Pasar al contenido principal

GENERACION CONSCIENTE DE TEXTOS

PID2021-123956OB-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Impulsar la Investigación Científico-Técnica y su Transferencia
Subprograma Subprograma Estatal de Generación de Conocimiento
Convocatoria Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Año convocatoria 2021
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE ALICANTE

Resultados relacionados

Resultados totales (Incluyendo duplicados): 55
Encontrada(s) 1 página(s)

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Computational and analytical analysis of integral-differential equations for modeling avoidance learning behavior

  • Turab, Ali
  • Montoyo, Andres
  • Nescolarde-Selva, Josué Antonio
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Nescolarde-Selva, Josué Antonio|||/items/bd921352-9e91-44d9-a574-4587b28566ba
This work emphasizes the computational and analytical analysis of integral-differential equations, with a particular application in modeling avoidance learning processes. Firstly, we suggest an approach to determine a unique solution to the given model by employing methods from functional analysis and fixed-point theory. We obtain numerical solutions using the approach of Picard iteration and evaluate their stability in the context of minor perturbations. In addition, we explore the practical application of these techniques by providing two examples that highlight the thorough analysis of behavioral responses using numerical approximations. In the end, we examine the efficacy of our suggested ordinary differential equations (ODEs) for studying the avoidance learning behavior of animals. Furthermore, we investigate the convergence and error analysis of the proposed ODEs using multiple numerical techniques. This integration of theoretical and practical analysis enhances the domain of applied mathematics by providing important insights for behavioral science research.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Beyond Generative Artificial Intelligence: Roadmap for Natural Language Generation

  • Miró Maestre, María
  • Martínez-Murillo, Iván
  • Martin, Tania Josephine
  • Navarro Colorado, Borja
  • Ferrández, Antonio
  • Suárez Cueto, Armando
  • Lloret, Elena
  • Ferrández, Antonio|||/items/b77d3a3a-c05b-4aa1-921f-a0f269e50ba1
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martin, Tania Josephine|||/items/58bfb24e-52da-4c1b-a00c-21281177e278
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
  • Suárez Cueto, Armando|||/items/63f12a3d-4bd9-4c83-b056-383e1645a62d
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
Generative Artificial Intelligence has grown exponentially as a result of Large Language Models (LLMs). This has been possible because of the impressive performance of deep learning methods created within the field of Natural Language Processing (NLP) and its subfield Natural Language Generation (NLG), which is the focus of this paper. Within the growing LLM family are the popular GPT-4, Bard and more specifically, tools such as ChatGPT have become a benchmark for other LLMs when solving most of the tasks involved in NLG research. This scenario poses new questions about the next steps for NLG and how the field can adapt and evolve to deal with new challenges in the era of LLMs. To address this, the present paper conducts a review of a representative sample of surveys recently published in NLG. By doing so, we aim to provide the scientific community with a research roadmap to identify which NLG aspects are still not suitably addressed by LLMs, as well as suggest future lines of research that should be addressed going forward.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Extracting Narrative Patterns in Different Textual Genres: A Multilevel Feature Discourse Analysis

  • Miró Maestre, María
  • Vicente, Marta
  • Lloret, Elena
  • Suárez Cueto, Armando
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Suárez Cueto, Armando|||/items/63f12a3d-4bd9-4c83-b056-383e1645a62d
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
We present a data-driven approach to discover and extract patterns in textual genres with the aim of identifying whether there is an interesting variation of linguistic features among different narrative genres depending on their respective communicative purposes. We want to achieve this goal by performing a multilevel discourse analysis according to (1) the type of feature studied (shallow, syntactic, semantic, and discourse-related); (2) the texts at a document level; and (3) the textual genres of news, reviews, and children’s tales. To accomplish this, several corpora from the three textual genres were gathered from different sources to ensure a heterogeneous representation, paying attention to the presence and frequency of a series of features extracted with computational tools. This deep analysis aims at obtaining more detailed knowledge of the different linguistic phenomena that directly shape each of the genres included in the study, therefore showing the particularities that make them be considered as individual genres but also comprise them inside the narrative typology. The findings suggest that this type of multilevel linguistic analysis could be of great help for areas of research within natural language processing such as computational narratology, as they allow a better understanding of the fundamental features that define each genre and its communicative purpose. Likewise, this approach could also boost the creation of more consistent automatic story generation tools in areas of language generation.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

What are Science Parks? working definitions and critical factors

  • Francés, Olga
  • Francés, Olga|||/items/174da0ee-29c0-4901-a69c-cfe706e01dce
This chapter examines the conceptual foundations, terminology and critical success factors of Science Parks (SPs), understood as a specific subgroup within the broader category of Science and Technology Parks (STPs). Although STPs are widely implemented as instruments to foster innovation and regional development, their heterogeneity and the absence of standardized definitions have generated ambiguity and inconsistent classifications. Through an extensive literature review and expert knowledge from the field, the chapter clarifies the terminology commonly associated with SPs, including distinctions among spin-offs, NTBFs, start-ups, incubators, accelerators, clusters, and other innovation-related environments. A novel and comprehensive definition of Science Parks is proposed, emphasizing the central role of universities, strong R&D orientation, and intensive knowledge, technology, and talent transfer. To identify the strategic elements that shape the performance of SPs, a structural analysis using MICMAC methodology is conducted. Sixteen factors extracted from the literature are evaluated, revealing five critical drivers: company profile, university–SP interaction, management strategy, number of participating firms, and the broader university ecosystem. The results highlight that SPs distinguish themselves from other STP models through the depth of their university involvement and the prioritization of innovative technology-based firms. The chapter concludes that an accurate conceptualization of SPs is essential for effective policymaking, improved park management, and the consistent development of innovation ecosystems.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A comprehensive methodology to construct standardised datasets for Science and Technology Parks

  • Francés, Olga
  • Fernández Martínez, Javier
  • Abreu Salas, José Ignacio
  • Gutiérrez, Yoan
  • Palomar, Manuel
  • Abreu Salas, José Ignacio|||/items/99fd9ec6-0b97-4c02-a28e-98bc309cff48
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Francés, Olga|||/items/174da0ee-29c0-4901-a69c-cfe706e01dce
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
This work presents a standardised approach to create datasets for Science and Technology Parks (STPs), facilitating future analysis of STP characteristics, trends and performance. STPs are the most representative examples of innovation ecosystems. The ETL (extraction-transformation-load) structure was adapted to a global field study of STPs. A selection stage and quality check were incorporated, and the methodology was applied to Spanish STPs. This study applies diverse techniques such as expert labelling and information extraction which uses language technologies. A novel methodology for building quality and standardised STP datasets was designed and applied to a Spanish STP case study with 49 STPs. An updatable dataset and a list of the main features impacting STPs are presented. Twenty-one (n = 21) core features were refined and selected, with fifteen of them (71.4 %) being robust enough for developing further quality analysis. The methodology presented integrates different sources with heterogeneous information that is often decentralised, disaggregated and in different formats: excel files, and unstructured information in HTML or PDF format. The existence of this updatable dataset and the defined methodology will enable powerful AI tools to be applied that focus on more sophisticated analysis, such as taxonomy, monitoring, and predictive and prescriptive analytics in the innovation ecosystems field.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Stability and numerical solutions for second-order ordinary differential equations with application in mechanical systems

  • Turab, Ali
  • Montoyo, Andres
  • Nescolarde-Selva, Josué Antonio
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Nescolarde-Selva, Josué Antonio|||/items/bd921352-9e91-44d9-a574-4587b28566ba
This study undertakes a comprehensive analysis of second-order Ordinary Differential Equations (ODEs) to examine animal avoidance behaviors, specifically emphasizing analytical and computational aspects. By using the Picard–Lindelöf and fixed-point theorems, we prove the existence of unique solutions and examine their stability according to the Ulam-Hyers criterion. We also investigate the effect of external forces and the system’s sensitivity to initial conditions. This investigation applies Euler and Runge–Kutta fourth-order (RK4) methods to a mass-spring-damper system for numerical approximation. A detailed analysis of the numerical approaches, including a rigorous evaluation of both absolute and relative errors, demonstrates the efficacy of these techniques compared to the exact solutions. This robust examination enhances the theoretical foundations and practical use of such ODEs in understanding complex behavioral patterns, showcasing the connection between theoretical understanding and real-world applications.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

OntoLM: Integrating Knowledge Bases and Language Models for classification in the medical domain, OntoLM: Integrando bases de conocimiento y modelos de lenguaje para clasificación en dominio médico

  • Yáñez Romero, Fabio
  • Montoyo, Andres
  • Muñoz, Rafael
  • Gutiérrez, Yoan
  • Suárez Cueto, Armando
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Muñoz, Rafael|||/items/d6ef1286-fc50-4e8b-9d97-bcbc30e3d1bc
  • Suárez Cueto, Armando|||/items/63f12a3d-4bd9-4c83-b056-383e1645a62d
  • Yáñez Romero, Fabio|||/items/792a2bc4-9249-45bf-8389-7a63e1b74671
Large language models have shown impressive performance in Natural Language Processing tasks, but their black box characteristics render the explainability of the model’s decision difficult to achieve and the integration of semantic knowledge. There has been a growing interest in combining external knowledge sources with language models to address these drawbacks. This paper, OntoLM, proposes a novel architecture combining an ontology with a pre-trained language model to classify biomedical entities in text. This approach involves constructing and processing graphs from ontologies and then using a graph neural network to contextualize each entity. Next, the language model and the graph neural network output are combined into a final classifier. Results show that OntoLM improves the classification of entities in medical texts using a set of categories obtained from the Unified Medical Language System. We can create more traceable natural language processing architectures using ontology graphs and graph neural networks.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Artificial Intelligence and Natural Language Processing Applied to Design

  • Villalba, María
Artificial Intelligence (AI) and Natural Language Processing (NLP) are transforming how designers approach and execute their tasks, fundamentally altering the landscape of various design disciplines, including industrial, fashion, interior, interface and visual communication design. This research explores how generative AI and NLP can significantly enhance the creativity and functionality of design processes. The goal is to investigate and develop applications of AI and NLP in design, evaluate the integration of these technologies into existing workflows, and address ethical considerations essential for sustainable innovation. By examining the intersection of AI and NLP in design, this research aims to develop a system that integrates these technologies to facilitate the creative process of designers and to establish practical guidelines.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

Chatbids, Asistente virtual especializado en Licitaciones públicas

  • Fernández Martínez, Javier
  • Gutiérrez, Yoan
  • Muñoz, Rafael
  • Montoyo, Andres
  • Palomar, Manuel
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Muñoz, Rafael|||/items/d6ef1286-fc50-4e8b-9d97-bcbc30e3d1bc
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
Chatbids es un asistente virtual basado en modelos de inteligencia artificial para facilitar la comprensión y acceso simplificado a las licitaciones de contratos públicos, en fuentes de información de la administración pública de la provincia de Alicante. Este sistema integra tecnologías del tipo RAG (Generación Aumentada por Recuperación), las cuales permiten procesar, analizar e indexar documentos de manera optimizada. Así, dichos documentos pueden ser consultados mediante un asistente de diálogo generativo. Chatbids facilita la ingestión continua de contenido a través de un proceso de indexación semántica. La interacción entre la base de datos de licitaciones y el usuario emplea un modelo de lenguaje abierto interno, lo que asegura que todo el flujo de información permanezca seguro dentro del sistema sin recurrir a servicios externos.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Team GPLSI at AuTexTification Shared Task: Determining the Authorship of a Text

  • Martínez-Murillo, Iván
  • Sepúlveda-Torres, Robiert
  • Saquete Boró, Estela
  • Lloret, Elena
  • Palomar, Manuel
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
AuTexTification is a shared task within the IberLEF workshop which aims to determine whether a text has been generated by an Artificial Intelligence (AI) or a human. The objective of this paper is to report the participation and results of the GPLSI team from the University of Alicante (Spain) in subtask 1: Human or Generated of the AuTexTification challenge for English and Spanish languages. We propose and experiment with different approaches based on Transfer Learning; Ensemble Learning; fine-tuning existing language models, such as RoBERTa or RemBERT; or relying on linguistic features. Our best models for both languages were trained through Transfer Learning techniques, obtaining the 6th and 8th position in the English and Spanish versions of this subtask, respectively. Results obtained in the Spanish-version were close to the top-performing team.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

An Approach to a Cost-Effective and Controllable Text Generation Architecture

  • Martínez-Murillo, Iván
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
Large Language Models (LLMs), which take advantage of the Transformers architecture, have obtained remarkable outcomes in the Generative Artificial Intelligence (AI) field. Specifically, these models have boosted the Natural Language Generation (NLG) field to new dimensions. Nonetheless, state-of-the-art NLG models also entail some challenges. Firstly, these models can generate text which may contain biased or hallucinated information, that can be used in an unethical way. Secondly, these models sometimes fail at generating commonsense knowledge, a fundamental factor in the human language. Thirdly, the expense of training LLMs is excessively high. Finally, most of the NLG research proposing more efficient architectures is focused on the English language. Thus, other languages such as Spanish still lack resources and models to address the NLG. Given the challenges mentioned above, the main objective of this paper is to provide a detailed research line that aims to propose an efficient and effective text generation architecture that could generate high-quality text in Spanish.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Analysing Linguistic Markers on Fake News to Enhance the Explainability of Deception Detection Systems

  • Pérez Montero, Alba
  • Pérez Montero, Alba|||/items/933a3a2a-82b5-4d6e-9337-2e478a6c3f42
The massive use of social media has increased the ease of dissemination of information. Unfortunately, every type of information can be massively disseminated (even deceptive information deliberately created to mislead). In this research we introduce a deep analysis of linguistic cues (i.e., adjectives, pronouns, complex syntax, emotion words, etc.) that can lead to distinguish which texts can be deceptive. The research focuses on extracting a combination of features: content-based, context-based, readability, virality and information richness. The objective is to test if current NLP tools for deception detection can extract in a satisfactory way these features and to examine the grade of explainability that these systems offer. The methodology starts from a multidisciplinary point of view, focusing in elaborate an integrative research. To pursue the objective of this research, we also combine both analytical and empirical methodologies. The expected impact is to enhance the ability to distinguish misinformation by improving the accuracy and transparency of deception detection systems for everyone.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

KD SENSO-MERGER: An architecture for semantic integration of heterogeneous data

  • Gutiérrez, Yoan
  • Abreu Salas, José Ignacio
  • Montoyo, Andres
  • Muñoz, Rafael
  • Estévez-Velarde, Suilan
  • Abreu Salas, José Ignacio|||/items/99fd9ec6-0b97-4c02-a28e-98bc309cff48
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Muñoz, Rafael|||/items/d6ef1286-fc50-4e8b-9d97-bcbc30e3d1bc
This paper presents KD SENSO-MERGER, a novel Knowledge Discovery (KD) architecture that is capable of semantically integrating heterogeneous data from various sources of structured and unstructured data (i.e. geolocations, demographic, socio-economic, user reviews, and comments). This goal drives the main design approach of the architecture. It works by building internal representations that adapt and merge knowledge across multiple domains, ensuring that the knowledge base is continuously updated. To deal with the challenge of integrating heterogeneous data, this proposal puts forward the corresponding solutions: (i) knowledge extraction, addressed via a plugin-based architecture of knowledge sensors; (ii) data integrity, tackled by an architecture designed to deal with uncertain or noisy information; (iii) scalability, this is also supported by the plugin-based architecture as only relevant knowledge to the scenario is integrated by switching-off non-relevant sensors. Also, we minimize the expert knowledge required, which may pose a bottleneck when integrating a fast-paced stream of new sources. As proof of concept, we developed a case study that deploys the architecture to integrate population census and economic data, municipal cartography, and Google Reviews to analyze the socio-economic contexts of educational institutions. The knowledge discovered enables us to answer questions that are not possible through individual sources. Thus, companies or public entities can discover patterns of behavior or relationships that would otherwise not be visible and this would allow extracting valuable information for the decision-making process.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Detecting Deception in Disinformation Across Languages: The Role of Linguistic Markers

  • Pérez Montero, Alba
  • Gargova, Silvia
  • Lloret, Elena
  • Moreda, Paloma
  • Pérez Montero, Alba|||/items/933a3a2a-82b5-4d6e-9337-2e478a6c3f42
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Gargova, Silvia|||/items/c1a7de66-9dd9-4506-8ab0-d3e7ba86bd27
The unstoppable proliferation of news driven by the rise of digital media has intensified the challenge of news verification. Natural Language Processing (NLP) offers solutions, primarily through content and context analysis. Recognizing the vital role of linguistic analysis, this paper presents a multilingual study of linguistic markers for automated deceptive disinformation detection across English, Spanish, and Bulgarian. We compiled datasets in these languages to extract and analyze both general and specific linguistic markers. We then performed feature selection using the SelectKBest algorithm, applying it to various classification models with different combinations of general and specific linguistic markers. The results show that Logistic Regression and Support Vector Machine classification models achieved F1-scores above 0.8 for English and Spanish. For Bulgarian, Random Forest yielded the best results with an F1-score of 0.73. While these markers demonstrate potential for transferability to other languages, results may vary due to inherent linguistic characteristics. This necessitates further experimentation, especially in low-resource languages like Bulgarian. These findings highlight the significant potential of our dataset and linguistic markers for multilingual deceptive news detection.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Multi3Generation: Multitask, Multilingual, and Multimodal Language Generation

  • Lloret, Elena
  • Barreiro, Anabela
  • Bhatt, Mehul
  • Bugarín-Diz, Alberto
  • Modoni, Gianfranco E.
  • Silberztein, Max
  • Calixto, Iacer
  • Korvel, Grăzina
  • Diamantaras, Konstantinos
  • Katsalis, Alkiviadis
  • Turuta, Oleskii
  • Russo, Irene
  • Erdem, Aykut
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
The purpose of this article is to highlight the critical importance of language generation today. In particular, language generation is explored from the following three aspects: multi-modality, multilinguality, which play crucial role for NLG community. We present the activities conducted within the Multi3Generation COST Action (CA18231), as well as current trends and future perspectives for multitask, multilingual and multimodal language generation.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Towards Intention-aligned Reviews Summarization: Enhancing LLM Outputs with Pragmatic Cues

  • Miró Maestre, María
  • Sepúlveda-Torres, Robiert
  • Estevanell-Valladares, Ernesto L.
  • Suárez Cueto, Armando
  • Lloret, Elena
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
  • Suárez Cueto, Armando|||/items/63f12a3d-4bd9-4c83-b056-383e1645a62d
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
Recent advancements in Natural Language Processing (NLP) have allowed systems to address complex tasks involving cultural knowledge, multi-step reasoning, and inference. While significant progress has been made in text summarization guided by specific instructions or stylistic cues, the integration of pragmatic aspects like communicative intentions remains underexplored, particularly in non-English languages. This study emphasizes communicative intentions as central to summary generation, classifying Spanish product reviews by intent and using prompt engineering to produce intention-aligned summaries. Results indicate challenges for large language models (LLMs) in processing extensive document clusters, with summarization accuracy heavily dependent on prior model exposure to similar intentions. Common intentions such as complimenting and criticizing are reliably handled, whereas less frequent ones like promising or questioning pose greater difficulties. These findings suggest that integrating communicative intentions into summarization tasks can significantly enhance summary relevance and clarity, thereby improving user experience in product review analysis.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Aproximación basada en inferencia lingüística y hechos estructurados para la detección de la alucinación en textos, An Approach Based on Linguistic Inference and Structured Facts for the Detection of Hallucinations in Texts

  • Madrigal Cutillas, Jairo
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
El objetivo de este artículo es proponer y evaluar un enfoque para detectar alucinaciones factuales en textos en español, combinando análisis lingüístico con verificación de hechos extraídos de fuentes de conocimiento estructurado, en nuestro caso, Wikidata. Los resultados obtenidos demuestran que el enfoque propuesto permite identificar contradicciones y hechos inventados con una alta precisión (alrededor del 90 %), ofreciendo una herramienta pionera y competitiva con respecto a herramientas similares para la verificación factual en español.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Communicative Intentions Annotation Scheme for Natural Language Processing Applications

  • Miró Maestre, María
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
Communicative intentions are one of the linguistic elements that usually determine the content of any message we want to express in our social interactions. With the purpose of contributing to the improvement of natural language processing systems, this thesis aims to create a communicative intention annotation scheme based on the taxonomy presented in the Speech Act Theory. In this way, language processing tools could consider communicative intentions as a starting point to help classify any message and its content depending first on the intention it reflects. To do so, the scheme will be created with the help of an already annotated corpus of Spanish tweets and subsequently evaluated by external annotators so that we can confirm the appropriateness and reliability of the tagged intentions before applying the scheme to an NLP system. Thus, it will be possible to check up to which point communicative intentions can improve the identification of the purpose of a message in an already created NLP system so that we can gain more linguistic information from any text automatically.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

La desambiguación y el razonamiento en la inteligencia artificial: Análisis lingüístico de ChatGPT

  • Pérez Montero, Alba
  • Pérez Montero, Alba|||/items/933a3a2a-82b5-4d6e-9337-2e478a6c3f42
En la actualidad las herramientas de generación de texto se están multiplicando debido al boom de la Inteligencia Artificial. Ejemplo de ello son los modelos GPT que se aplican a diferentes plataformas de generación de texto e ideas. En este trabajo se presenta un estudio experimental acerca de la capacidad de desambiguación y razonamiento de la herramienta de generación de texto ChatGPT. Se trata de un experimento metódico en que se realiza tanto un análisis cuantitativo como cualitativo, por lo que se adopta una perspectiva integradora que enriquece el análisis de la herramienta ChatGPT. Para llevar a cabo esta investigación se realiza una revisión de la literatura acerca de las herramientas de generación de texto dentro de la disciplina de la Lingüística Computacional y se presentan algunos conceptos básicos en relación con la Lingüística Teórica y algunas subdisciplinas como la Sintaxis, la Semántica o la Pragmática. El objetivo principal del trabajo es probar la actuación de ChatGPT ante oraciones que contienen algún elemento que produce ambigüedad en la interpretación, tanto en inglés como en español. Para ello, se delimitan una serie de casos en los que se produce una ambigüedad, basándonos en el esquema de Winograd. Finalmente se realiza una encuesta para comparar los resultados sobre la capacidad de desambiguación de ChatGPT con la capacidad humana.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Where and How as Key Factors for Knowledge-Enhanced Constrained Commonsense Generation

  • Martínez-Murillo, Iván
  • Moreda, Paloma
  • Lloret, Elena
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
This paper addresses a key limitation in Natural Language Generation (NLG) systems: their struggle with commonsense reasoning, which is essential for generating contextually appropriate and plausible text. The study proposes an approach to enhance the commonsense reasoning abilities of NLG systems by integrating external knowledge framed in a constrained commonsense generation task. The paper investigates strategies for extracting and injecting external knowledge into pre-trained models, specifically BART and T5, in both base and large configurations. Experimental results show that incorporating external knowledge, extracted using a simple strategy, leads to significant performance improvements, with the models achieving 88% accuracy in generating plausible and correct sentences. When refined methods for knowledge extraction are applied, the accuracy further increases to 92%. These findings underscore the crucial role of high-quality external knowledge in enhancing the commonsense reasoning capabilities of NLG systems, suggesting that such integration is vital for advancing their performance in real-world applications.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Aprovechamiento de ChatGPT en la enseñanza de lengua extranjera en educación superior

  • Ribes-Lafoz, María
  • Navarro Colorado, Borja
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
  • Ribes-Lafoz, María|||/items/1f2fbcb5-ac19-4f85-ab9f-d347f30a1f64
The last decade has witnessed a remarkable advancement in the field of Artificial Intelligence, particularly in Natural Language Processing (NLP) and Natural Language Generation (NLG), which has been made possible by the development and enhancement of Deep Learning techniques and Large Language Models (LLMs). Nowadays, ChatGPT is one of the most widely known and used, an advanced AI tool designed to understand and generate human-like text based on a vast amount of data. In this work we put forward an innovative proposal for higher education which involves the use of ChatGPT-3 as a supervised tool in the classroom which will be mostly employed by students and not by teachers, in order to foster their linguistic skills by means of transforming the automatically generated written text into an oral presentation to be delivered in front of the class. Our ultimate goal is not to determine whether the student has made fraudulent use of GPT, but rather to leverage all the advantages that it can offer to improve the teaching and learning process of a foreign language within the CLIL framework.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A review of AI application trends in industrial design

  • Villalba, María
  • Palomar, Manuel
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
This article presents a comprehensive literature review of recent trends in the application of Artificial Intelligence (AI) in the industrial design arena. The review primarily focuses on studies published since 2017, selected from high-quality Q1 and Q2 journals accessed through databases such as Science Direct, Scopus, and IEEE Explore. The review employed the ‘Targeted Literature Review’ methodology, ensuring a focused and relevant analysis of AI applications in industrial design. Key trends identified include the use of Machine Learning (ML) and Natural Language Processing (NLP) for extracting customer requirements, Deep Learning (DL) for generating design alternatives, and optimization algorithms for improving product prototypes. Notably, AI tools are not only automating routine design tasks but also emerging as creative collaborators, significantly enhancing human-technology interaction. The findings highlight AI’s ability to optimize design processes, streamline collaboration between human designers and AI systems, and redefine the boundaries of innovation in industrial design.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Towards an Efficient Approach for Controllable Text Generation

  • Martínez-Murillo, Iván
  • Moreda, Paloma
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
Since the emergence of Transformers architecture, the Natural Language Generation (NLG) field has advanced at breakneck speed. Large language models (LLMs) have achieved remarkable results in the field of generative artificial intelligence (AI). Nevertheless, they also present some problems worth analysing: not only are they computationally non-viable to academia, but they also have other issues, such us not generating text in a fully controllable way or the phenomenon known as hallucination. Because of this, the purpose of this paper is to outline and set the ideas for a new PhD thesis research. This PhD thesis will aim at advancing the state of the art by discovering new cost-effective, efficient and high-performing approaches to controlled text generation that could perform well in the different NLG tasks. Therefore, the main objective of this PhD thesis is to design a novel and efficient task-agnostic architecture that could obtain equivalent performance of LLMs, while generating text in a controllable way and including external commonsense knowledge.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Experiencias con el proyecto COST Action Distant Reading for European Literary History (CA16204) y el desarrollo del corpus ELTeC

RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Contextual word embeddings for tabular data search and integration

  • Pilaluisa, José
  • Tomás, David
  • Navarro Colorado, Borja
  • Mazón, Jose-Norberto
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
This paper presents a new approach to retrieve and further integrate tabular datasets (collections of rows and columns) using union and join operations. In this work, both processes were carried out using a similarity measure based on contextual word embeddings, which allows finding semantically similar tables and overcome the recall problem of lexical approaches based on string similarity. This work is the first attempt to use contextual word embeddings in the whole pipeline of table search and integration, including for the first time their use in the join operation. A comprehensive analysis of their performance was carried out on both retrieving and integrating tabular datasets, comparing them with context-free models. Column headings and cell values were used as contextual information and their impact on each task was evaluated. The results revealed that contextual models significantly outperform context-free models and a traditional weighting schema in ad hoc table retrieval. In the data integration task, contextual models also improved the results on union operation compared to context-free approaches.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Controllability and integration of external knowledge as key factors in the development of efficient natural language generation models

  • Martínez-Murillo, Iván
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
La Generación del Lenguaje Natural (GLN) es un área fundamental dentro del Procesamiento del Lenguaje Natural (PLN) que busca permitir a las máquinas producir textos coherentes, contextualmente adecuados y comprensibles para los humanos. Para que un sistema de GLN sea exitoso, no solo debe generar oraciones gramaticalmente correctas, sino que también debe incorporar sentido común, es decir, el conocimiento básico y el razonamiento intuitivo sobre el mundo que las personas usamos para entender y comunicar ideas con sentido. El sentido común es crucial en esta tarea porque permite que los modelos no solo imiten patrones lingüísticos, sino que produzcan contenido con coherencia lógica y factual, evitando errores que son comunes cuando los sistemas generan información sin una comprensión real del contexto o del conocimiento implícito. La tesis doctoral aquí presentada aborda precisamente ese desafío, centrándose en cómo mejorar las capacidades de razonamiento por sentido común en los modelos de GLN. En particular, el trabajo de investigación realizado en esta tesis doctoral realiza varias contribuciones importantes dentro del ámbito de la GLN con sentido común, enfocándose especialmente en el contexto multilingüe. En primer lugar, se desarrollaron dos recursos fundamentales para la comunidad investigadora: los datasets COCOTEROS y MULTICOM. COCOTEROS es un corpus en español diseñado específicamente para la generación de texto con sentido común que incluye información contextual para mejorar la coherencia y adecuación pragmática del lenguaje generado. Este dataset fue creado mediante una metodología semiautomática que incluye generación de contextos con modelos de lenguaje grande y validación tanto manual como automática para asegurar la calidad lingüística y minimizar sesgos de género. Por otro lado, MULTICOM amplía esta perspectiva a un contexto multilingüe, permitiendo evaluar y comparar las capacidades de razonamiento de sentido común en diferentes idiomas, lo que facilita entender las limitaciones y peculiaridades que presentan los modelos en diversas lenguas. Además, la tesis aporta un análisis detallado sobre el desempeño de los grandes modelos de lenguaje (LLMs) en tareas de generación con sentido común en varios idiomas. Este estudio revela cómo las diferencias lingüísticas pueden afectar significativamente la capacidad de los modelos para generar textos con sentido común adecuado, lo que subraya la necesidad de desarrollar métodos específicos y recursos multilingües para mejorar la generación de texto más allá del inglés. El aporte central de esta tesis es el método Knowledge Retrieval and Injection Generation (KRAIG), una estrategia para recuperar conocimiento pertinente y luego integrarlo durante el proceso de generación de texto en los modelos GLN. KRAIG permite superar limitaciones comunes en los modelos actuales relacionados con la producción de textos sin sentido común o incoherentes, conectando el conocimiento externo relevante con el contexto y las necesidades específicas de la tarea. Este método se valida a través de experimentos en diferentes dominios, incluyendo escenarios de generación narrativa, demostrando su eficacia y versatilidad para mejorar la fidelidad, coherencia y capacidad de razonamiento en sistemas de generación automática de texto. En conjunto, estas contribuciones ofrecen un avance sustancial para la GLN con sentido común, proporcionando tanto herramientas prácticas como marcos teóricos para enriquecer y evaluar los modelos multilingües, y estableciendo un camino para integrar conocimiento externo de manera efectiva en los sistemas de generación de texto.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Assessing the potential of LLMs as crowdworkers for contextual information generation

  • Martínez-Murillo, Iván
  • Miró Maestre, María
  • Suárez Cueto, Armando
  • Lloret, Elena
  • Moreda, Paloma
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Suárez Cueto, Armando|||/items/63f12a3d-4bd9-4c83-b056-383e1645a62d
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
Large Language Models (LLMs) have shown remarkable capabilities, demonstrating their potential to transform the Natural Language Processing (NLP) field by achieving strong performance across the entire spectrum of tasks. In this context, there is growing interest in leveraging LLMs as automated crowdworkers to streamline the traditionally labor-intensive process of manual annotation and linguistic content generation. This paper specifically examines the feasibility of using LLMs to generate high-quality contextual information — an increasingly recognized element for enhancing generative systems — by producing linguistic contexts from given premise sentences. We evaluate four prominent LLMs — LLaMA 2, PaLM 2, Vicuna, and GPT-3.5 — by making them generate 180 contextual outputs, which are then compared to 60 contexts manually crafted by linguistic experts. To systematically assess the appropriateness of these generated contexts, we introduce CATS (Contextual Appropriateness in Texts for Spanish), a novel and adaptable evaluation metric for measuring the appropriateness of contextual information generated texts. CATS is rooted in established discourse theories and provides a robust framework for analyzing linguistic context quality. The implementation of CATS is made publicly available at https://github.com/gplsi/cats. The reliability of CATS is validated through a manual evaluation conducted by two independent human referees. The results indicate that the quality of contexts generated by LLMs is comparable to those produced by human specialists, as evidenced by both CATS scores (0.214 vs. 0.150) and human judgment. Our findings underscore the efficiency and cost-effectiveness of employing LLMs as alternatives to human crowdworkers for generating contextual information, offering promising implications for the scalability and advancement of generative systems.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Cross-sectional analysis of large language models in current natural language generation challenges

  • Miró Maestre, María
  • Martínez-Murillo, Iván
  • Morote Martínez, Aitana
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
The rapid evolution of Large Language Models (LLMs) has produced diverse model families with multiple versions differing in parameter size and release chronology. While this ongoing progress has driven substantial advancements in Natural Language Generation (NLG), several critical challenges remain unmet. This paper presents a cross-sectional analysis of 24 model versions from five prominent LLM families, evaluating their performance across five persistent generation gaps. For each gap, we define three targeted tasks to systematically assess model behaviour, with three prompt variants per task to analyse them with comprehensive examples, yielding 45 distinct prompts and 1080 model responses. Human expert qualitative analysis reveals that gpt-4o and gpt-40-mini accurately respond to 75.5% and 46.6% of prompts respectively, while models as llama-3.2-3b-instruct and llama-3.2-1b-instruct achieve only 11% and 10% accuracy respectively. Our study also highlights a key and unexpected insight: in several cases, earlier or smaller LLM versions sometimes match or exceed the performance of their latest, larger counterparts. These findings invite a timely discussion within the NLG community about the current trajectory of scaling models versus focusing on the optimisation and adaptation of existing architectures. We hope this analysis contributes valuable perspectives for more informed and strategic development of future LLMs in the field of NLG.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A multifaceted approach to detect gender biases in Natural Language Generation

  • Consuegra-Ayala, Juan Pablo
  • Martínez-Murillo, Iván
  • Lloret, Elena
  • Moreda, Paloma
  • Palomar, Manuel
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Consuegra-Ayala, Juan Pablo|||/items/5a98e4ca-607f-4aa0-91c2-a5d929bab52c
Recent advances in generative models have skyrocketed the popularity of conversational chatbots and have revolutionized the way we interact with artificial intelligence. At the same time, research has shown that machine learning models can unconsciously reflect and amplify human biases. This is particularly dangerous for generative models given the huge popularity of such technologies. Specifically, a fundamental source of bias of such technologies is the resources on which the models are trained. To address this issue, this paper proposes a methodology to analyze intrinsic gender bias in Natural Language Generation (NLG). Some works already propose metrics and approaches to measure bias in the Natural Language processing field. However, there is a lack of standard methodology to measure gender bias in NLG. Therefore, adapting the Bias Score approach, our proposal involves three sequential stages applied to individual texts to detect intrinsic gender bias on NLG effectively. Those steps are as follows: (i) word scoring; (ii) word filtering; and (iii) generative-word analysis. This methodology is applied to recent datasets and pre-trained models widely used for the generation of text with common sense. In particular, this paper analyzes the potential gender bias in CommonGen and C2 Gen datasets and the SimpleNLG and T5 models. The results show the ability of the proposed methodology to detect gender bias in word distributions, presenting a strong correlation with the words typically associated with a specific gender. Results indicate that both tested datasets are intrinsically gender-biased, and therefore, tested models fine-tuned with those datasets also are.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Analytical and Numerical Analysis of a Memory-Dependent Fractional Model for Behavioral Learning Dynamics

  • Turab, Ali
  • Nescolarde-Selva, Josué Antonio
  • Ali, Wajahat
  • Montoyo, Andres
  • Tiang, Jun-Jiat
  • Nescolarde-Selva, Josué Antonio|||/items/bd921352-9e91-44d9-a574-4587b28566ba
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
Fractional differential equations offer a natural framework for describing systems in which present states are influenced by the past. This work presents a nonlinear Caputo-type fractional differential equation (FDE) with a nonlocal initial condition and attempts to describe a model of memory-dependent behavioral adaptation. The proposed framework uses a fractional-order derivative 𝜂∈(0,1) to discuss the long-term memory effects. The existence and uniqueness of solutions are demonstrated by Banach’s and Krasnoselskii’s fixed-point theorems. Stability is analyzed through Ulam–Hyers and Ulam–Hyers–Rassias benchmarks, supported by sensitivity results on the kernel structure and fractional order. The model is further employed for behavioral despair and learned helplessness, capturing the role of delayed stimulus feedback in shaping cognitive adaptation. Numerical simulations based on the convolution-based fractional linear multistep (FVI–CQ) and Adams–Bashforth–Moulton (ABM) schemes confirm convergence and accuracy. The proposed setup provides a compact computational and mathematical paradigm for analyzing systems characterized by nonlocal feedback and persistent memory.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Team GPLSI at QClef 2025: Quantum-Inspired Instance Selection and Clustering: Notebook for the QuantumCLEF Lab at CLEF 2025

  • Consuegra-Ayala, Juan Pablo
  • Morote Martínez, Aitana
  • Valero-Abellón, Francisco
  • Lloret, Elena
  • Moreda, Paloma
  • Palomar, Manuel
  • Consuegra-Ayala, Juan Pablo|||/items/5a98e4ca-607f-4aa0-91c2-a5d929bab52c
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Valero-Abellón, Francisco|||/items/18293e1a-c0d0-47d1-8e2d-78155a00e219
This paper presents the participation of the GPLSI team in the Quantum CLEF (QClef) Lab at CLEF 2025, focusing on Task 2 - Instance Selection and Task 3 - Clustering. The QClef Lab explores the applicability of quantum and quantum-inspired techniques to core AI tasks, emphasizing optimization efficiency and data reduction. In Task 2, we propose three multi-paradigm approaches for selecting representative training instances for sentiment classification, leveraging sentiment-aware pairing, local set-based criteria, and classical heuristics. In Task 3, we introduce a single quantum-inspired clustering framework that integrates four distinct pivot selection strategies for document grouping in embedding space. Our methods achieved competitive performance across both tasks. In particular, our LocalSets method achieved the highest effectiveness in Task 2 while substantially reducing the training set, and our FPS-Medoids approach delivered the best results for Task 3 in terms of nDCG@10. Overall, our findings support the potential of annealing-based techniques to deliver effective trade-offs between performance and computational efficiency in realistic machine learning pipelines.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

The Simplification of the Language of Public Administration: The Case of Ombudsman Institutions

  • González Delgado, Gabriel
  • Navarro Colorado, Borja
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
Language produced by Public Administrations has crucial implications in citizens’ lives. However, its syntactic complexity and the use of legal jargon, among other factors, make it difficult to be understood for laypeople and certain target audiences. The NLP task of Automatic Text Simplification (ATS) can help to the necessary simplification of this technical language. For that purpose, specialized parallel datasets of complex-simple pairs need to be developed for the training of these ATS systems. In this position paper, an on-going project is presented, whose main objectives are (a) to extensively analyze the syntactical, lexical, and discursive features of the language of English-speaking ombudsmen, as samples of public administrative language, with special attention to those characteristics that pose a threat to comprehension, and (b) to develop the OmbudsCorpus, a parallel corpus of complex-simple supra-sentential fragments from ombudsmen’s case reports that have been manually simplified by professionals and annotated with standardized simplification operations. This research endeavor aims to provide a deeper understanding of the simplification process and to enhance the training of ATS systems specialized in administrative texts.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Roadmap for Natural Language Generation: Challenges and Insights, Próximos Pasos en la Generación del Lenguaje Natural: Desafíos y Enfoques por Explorar

  • Miró Maestre, María
  • Martínez-Murillo, Iván
  • Martin, Tania Josephine
  • Navarro Colorado, Borja
  • Ferrández, Antonio
  • Suárez Cueto, Armando
  • Lloret, Elena
  • Ferrández, Antonio|||/items/b77d3a3a-c05b-4aa1-921f-a0f269e50ba1
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martin, Tania Josephine|||/items/58bfb24e-52da-4c1b-a00c-21281177e278
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
  • Suárez Cueto, Armando|||/items/63f12a3d-4bd9-4c83-b056-383e1645a62d
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
Generative Artificial Intelligence has experienced exponential growth largely due to the advent of Large Language Models (LLMs). This expansion is fueled by the impressive performance of deep learning methods used in Natural Language Processing (NLP) and its subfield, Natural Language Generation (NLG), which is the focus of this paper. Popular LLMs, such as GPT-4, Bard, and tools such as ChatGPT have set benchmarks for addressing various NLG tasks. This scenario raises critical questions regarding the future of NLG and its adaptation to emerging challenges in the LLM era. To explore these issues, the present paper reviews a representative sample of recent NLG surveys, thereby providing the scientific community with a research roadmap to identify NLG aspects that remain inadequately addressed and to suggest areas warranting further in-depth exploration in NLG.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Procesamiento automático de la pragmática en español a partir de las intenciones comunicativas

  • Miró Maestre, María
El nivel de análisis pragmático del lenguaje está considerado como uno de los más complejos debido, entre otros aspectos, a los matices inferenciales y contextuales que procesamos los humanos para llegar a comprender el significado real de cualquier mensaje. Esta dificultad no pasa desapercibida en la disciplina del Procesamiento del Lenguaje Natural (PLN), ya que desde sus inicios, los investigadores dedicados al procesamiento de cualquier lengua se han topado con diversos obstáculos de naturaleza pragmática a la hora de enseñar a los sistemas de aprendizaje cualquier idioma. De hecho, así como la teoría lingüística sitúa la pragmática en el último nivel de análisis para la comprensión de un mensaje, la teoría en lingüística computacional también pone la noción de pragmática en un segundo plano. Esto no ocurre por falta de interés o de importancia de este nivel a la hora de procesar el lenguaje, sino por las dificultades añadidas que implica el análisis pragmático y la falta de recursos lingüísticos que ayuden a su estudio en diferentes lenguas. Entre ellas, las incursiones que se han hecho en el estudio de la pragmática en español con fines computacionales han ido generalmente dirigidas a la creación de sistemas de diálogo. No obstante, existe una carencia de recursos enfocados en la pragmática del español encuadrados en la comunicación escrita, sobre todo dentro de los géneros textuales englobados en la comunicación mediada por ordenador. El estudio de los diferentes fenómenos pragmáticos en el lenguaje escrito permite comprender con más información contextual las opiniones de los usuarios en el entorno digital cuando expresan y comparten sus pensamientos con el resto de la comunidad. El analizar aspectos pragmáticos de la forma de expresarse de los usuarios en estos entornos puede ser de gran ayuda para que los sistemas creados en el área de PLN sepan reconocer y generar respuestas acordes con la información pragmática detectada en el mensaje original. En este sentido, la propia disciplina de PLN se convierte en una aliada para crear recursos lingüísticos de calidad, rigurosos y adaptados al objetivo de identificar esos patrones lingüísticos de naturaleza pragmática automáticamente. La presente investigación supone, pues, la combinación del conocimiento lingüístico que se tiene actualmente respecto al nivel pragmático del español junto con la aplicación de las últimas técnicas de aprendizaje automático propias del contexto computacional para estudiar uno de los fenómenos lingüísti cos que sustentan el nivel pragmático del lenguaje: las intenciones comunicativas. Para ello, partimos de la la premisa de que el análisis de los patrones que ayudan a los humanos a identificar las intenciones comunicativas del español puede ser de gran ayuda para los sistemas de aprendizaje automático a la hora de descubrir información pragmática de cualquier mensaje que ayude a su comprensión, además de a la generación automática de mensajes preservando el componente natural de la lengua. A partir de la investigación aquí realizada, se ofrecen dos recursos lingüísticos enfocados en el análisis de las intenciones comunicativas en español. Por un lado, se diseña una guía de anotación de intenciones comunicativas en dos dimensiones discursivas, estas son, la global (que vendría a ser la intención de un mensaje completo) y la segmental (centrada en la intención de cada uno de los segmentos enunciativos que componen ese mismo mensaje). Con ella, y a partir de estrategias de anotación semiautomática propias del área del PLN, se consigue crear el corpus INTENT-ES. Se trata del primer corpus en español de mensajes procedentes de la red social Twitter (conocida actualmente como ‘X’) anotados con sus intenciones comunicativas tanto globales como segmentales. A partir de estos dos recursos, se procede a la evaluación de los modelos de aprendizaje y generación utilizados ampliamente en el PLN para comprobar hasta qué punto pueden tanto clasificar como generar las intenciones comunicativas dependiendo del objetivo de investigación. De este modo, este trabajo ofrece un análisis exhaustivo para constatar hasta dónde han evolucionado estos modelos a la hora de integrar la información pragmática en su conocimiento interno, así como qué caminos futuros se deben abordar para minimizar los obstáculos relacionados con el estudio de la pragmática en el ámbito computacional. Las aportaciones realizadas a partir de esta investigación suponen un paso adelante en la incorporación de la pragmática en los sistemas de aprendizaje propios de la disciplina de PLN para fomentar la investigación en lingüística computacional desde una perspectiva pragmática. Además, consideramos que los recursos diseñados en el transcurso de este trabajo servirán de gran ayuda para que experimentos futuros cuenten con recursos de base pragmática. Así, conseguiremos aportar más información fundamental a los modelos que les haga mejorar su rendimiento en las diferentes tarea de clasificación o generación que ofrece esta disciplina.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Leading and non-leading prompts: Quantifying gender bias in Large Language Models through BiasBloom corpus

  • Muñoz García, Victoria
  • Consuegra-Ayala, Juan Pablo
  • Moreda, Paloma
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Consuegra-Ayala, Juan Pablo|||/items/5a98e4ca-607f-4aa0-91c2-a5d929bab52c
  • Muñoz García, Victoria|||/items/8c62b8e1-712b-4343-b99e-aa8b0e7d4fe6
The increasing use of Artificial Intelligence by non-experts underscores the need to address biases in its outputs, particularly in gendered languages like Spanish, where linguistic features reflect gender. This paper proposes a validated methodology to quantify gender bias in text generated by Large Language Models (LLMs) in Spanish. The approach involves creating gendered seed-word lists, building a Spanish-specific corpus using curated prompts, and analyzing gender polarity and co-occurrences within the generated text. Validated using five state-of-the-art LLMs—GPT-3.5, GPT-4o, Llama 3, Gemini 1.5, and Mixtral8x7b—this study provides a systematic framework for bias detection in Spanish and highlights differences in model performance. By addressing the challenges of bias in gendered languages, this research aims to contribute to the development of equitable AI systems and advances methodologies for bias quantification. The findings highlight gender disparities in LLMs, with masculine and feminine biases shifting depending on the discourse structure. Specifically, the analysis reveals a prevalence of masculine biases in non-leading prompts and feminine biases in leading prompts, underscoring the nuanced ways in which prompt positioning can influence gender representation in model outputs.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

XatDocs: Software RAG para el Procesamiento e Interrogación Semántica de Repositorios de Documentos

  • Gutiérrez, Yoan
  • Fernández Martínez, Javier
  • Montoyo, Andres
  • Muñoz, Rafael
  • Palomar, Manuel
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Muñoz, Rafael|||/items/d6ef1286-fc50-4e8b-9d97-bcbc30e3d1bc
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
XatDocs es un software informático tipo RAG (Retrieval Augmented Generation) que procesa, analiza e indexa documentos de forma optimizada y semántica para posteriormente interrogar dichos documentos a través de una asistente de diálogo generativo. XatDocs permite ingerir contenido continuamente y a través de un proceso de indexación semántico. Respecto a la interacción entre la base de datos y el usuario se utiliza un modelo de lenguaje abierto local, lo cual garantiza que todo el flujo de información se conserve de forma segura dentro del sistema sin utilizar servicios de terceros.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Evaluación multilingüe de la desambiguación referencial en la IA Generativa mediante el esquema de Winograd, Multilingual Evaluation of Referential Disambiguation in Generative AI Using Winograd Schema

  • Pérez Montero, Alba
  • Lloret, Elena
  • Moreda, Paloma
  • Pérez Montero, Alba|||/items/933a3a2a-82b5-4d6e-9337-2e478a6c3f42
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
El auge de los agentes conversacionales, como ChatGPT, abren un interesante camino para analizar la Generación del Lenguaje Natural. Por ello, en este estudio experimental se examina la capacidad de desambiguación referencial de diversos agentes conversacionales. Se aborda la investigación desde la perspectiva de la Lingüística Computacional para analizar una de las tareas más complejas para el Procesamiento del Lenguaje Natural. En concreto, se evalúa la efectividad de sistemas de IA generativa en la interpretación de oraciones que contienen ambigüedad referencial en inglés, español y valenciano. Se utiliza el esquema de Winograd como punto de partida para crear datasets multilingües con ejemplos de diferentes niveles de ambigüedad referencial. La relevancia de este artículo reside en el análisis de la desambiguación referencial en profundidad y su perspectiva multilingüe. La experimentación se lleva a cabo mediante dos pruebas: en la primera se usan enunciados que contienen una palabra desambiguadora que guía la interpretación y en la segunda esta palabra se elimina. Los resultados demuestran que al prescindir de una palabra desambiguadora ninguno de los agentes conversacionales supera un 0.6 de precisión en ninguno de los idiomas. De esta manera, se concluye que la tarea de desambiguación referencial resulta difícil de resolver para la IA generativa en los casos en que no existe suficiente información contextual.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

CuentosIE: can a chatbot about “tales with a message” help to teach emotional intelligence?

  • Ferrández, Antonio
  • Lavigne Cerván, Rocio
  • Peral, Jesús
  • Navarro Soria, Ignasi
  • Lloret, Ángel
  • Gil, David
  • Rocamora-Rodríguez, María C.
  • Ferrández, Antonio|||/items/b77d3a3a-c05b-4aa1-921f-a0f269e50ba1
  • Gil, David|||/items/90b814a5-7a43-4cc4-bd20-9a77d5ff0f08
  • Lloret, Ángel|||/items/f87b9fb9-6755-4011-8dc5-af571153e1f5
  • Navarro Soria, Ignasi|||/items/1c7c4096-530f-4487-8b9c-e472938c5df6
  • Peral, Jesús|||/items/c944ebfe-a23a-4bde-b779-e2054a62d1a7
  • Rocamora-Rodríguez, María C.|||/items/860042c9-93c8-45e7-b00f-98172f389073
In this article, we present CuentosIE (TalesEI: chatbot of tales with a message to develop Emotional Intelligence), an educational chatbot on emotions that also provides teachers and psychologists with a tool to monitor their students/patients through indicators and data compiled by CuentosIE. The use of “tales with a message” is justified by their simplicity and easy understanding, thanks to their moral or associated metaphors. The main contributions of CuentosIE are the selection, collection, and classification of a set of highly specialized tales, as well as the provision of tools (searching, reading comprehension, chatting, recommending, and classifying) that are useful for both educating users about emotions and monitoring their emotional development. The preliminary evaluation of the tool has obtained encouraging results, which provides an affirmative answer to the question posed in the title of the article.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Tailoring a Knowledge Discovery Framework to Process Pharmacologic Documents, Adaptación de un Marco de Descubrimiento de Conocimiento para Procesar Documentos Farmacológicos

  • Moreno, Isabel
  • Piad-Morffis, Alejandro
  • Gutiérrez, Yoan
  • Moreda, Paloma
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
This paper introduces a specialized knowledge discovery framework designed to process health technical documents and extract knowledge. The framework improves existing technology, known as LETO, through the integration of CARMEN, a multilingual entity classification system capable of infusing health-related semantics into the initial versatile approach. This collaborative approach enables the generation of domain-specific knowledge graphs for two languages, Spanish and English. Additionally, this provides a valuable means by which to explore relationships within the health domain that could otherwise remain undiscovered. The resulting technology is subjected to an evaluation procedure using standard metrics employed in knowledge discovery tasks, illustrating how CARMEN contributes to an augmentation in the knowledge discovered in LETO. Thus, the generated knowledge graph can be leveraged for the creation of explanatory representation techniques, facilitating a more comprehensive articulation of human knowledge and potentially serving, among other purposes, as an educational resource.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Edición digital enriquecida: un modelo de anotación multinivel para poesía del Siglo de Oro, Enriched Digital Edition: a Multilevel Annotation Model for Golden-Age Spanish Poetry

  • Navarro Colorado, Borja
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
En este capítulo se presenta un modelo general para la anotación multinivel de corpora de texto literario. Por multinivel se hace referencia a la combinación, en un mismo corpus, de información de diferentes niveles de descripción lingüística o literaria, desde datos relacionados con palabras o sílabas, hasta cuestiones temáticas, textuales o pragmáticas. El objetivo final de un corpus de estas características es fijar un posible análisis literario, por lo que se considera como una edición digital enriquecida. Se defienden cuatro características que un corpus de texto literario debe cumplir: interoperabilidad, perspectivismo, unidad y claridad/sencillez. Se da cuenta de los principales problemas de formalización en un corpus multinivel de este tipo: la combinación de diferentes formalismos de representación y, en el caso de XML, el problema de un anidamiento incorrecto. Finalmente se propone un modelo para un corpus de poesía del Siglo de Oro.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Automatic annotation of protected attributes to support fairness optimization

  • Consuegra-Ayala, Juan Pablo
  • Gutiérrez, Yoan
  • Almeida-Cruz, Yudivian
  • Palomar, Manuel
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Consuegra-Ayala, Juan Pablo|||/items/5a98e4ca-607f-4aa0-91c2-a5d929bab52c
Recent research has shown that the unaware automation of high-risk decision-making tasks can result in unfair decisions being made. The most common approaches to address this problem adopt definitions of fairness based on protected attributes. Precise annotation of protected attributes enables the application of bias mitigation techniques to commonly unlabeled kinds of data (e.g., images, text, etc.). This paper proposes a framework to automatically annotate protected attributes in data collections. The framework focuses on providing a single interface to annotate protected attributes of different types (e.g., gender, race, etc.) and from different kinds of data. Internally, the framework coordinates multiple sensors to produce the final annotation. Several sensors for textual data are proposed. An optimization search technique is designed to tune the framework to specific domains. Additionally, a small dataset of movie reviews —annotated with gender and sentiment— was created. The evaluation in datasets of texts from diverse domains shows the quality of the annotations and their effectiveness to be used as a proxy to estimate fairness in datasets and machine learning models. The source code is available online for the research community.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Computational and Parameter-Sensitivity Analysis of Dual-Order Memory-Driven Fractional Differential Equations with an Application to Animal Learning

  • Turab, Ali
  • Nescolarde-Selva, Josué Antonio
  • Ali, Wajahat
  • Montoyo, Andres
  • Tiang, Jun-Jiat
  • Nescolarde-Selva, Josué Antonio|||/items/bd921352-9e91-44d9-a574-4587b28566ba
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
Fractional differential equations are used to model complex systems where present dynamics depend on past states. In this work, we study a linear fractional model with two Caputo orders that captures long-term memory together with short-term adaptation. The existence and uniqueness of solutions are established using Banach and Krasnoselskii’s fixed-point theorems. A parameter study isolates the roles of the fractional orders and coefficients, yielding an explicit stability region in the (𝛼,𝛽) –plane via computable contraction bounds. For computation, we implement the Adams–Bashforth–Moulton (ABM) and fractional linear multistep (FLM) methods, comparing accuracy and convergence. As an application, we model animal learning in which proficiency evolves under memory effects and pulsed stimuli. The results quantify the impact of feedback timing on trajectories within the admissible region, thereby illustrating the suitability of dual-order fractional models for memory-driven behavior.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Deep neural networks and stochastic methods for cognitive modeling of rat behavioral dynamics in T-mazes

  • Turab, Ali
  • Nescolarde-Selva, Josué Antonio
  • Ullah, Farhan
  • Montoyo, Andres
  • Alfiniyah, Cicik
  • Sintunavarat, Wutiphol
  • Rizk, Doaa
  • Zaidi, Shujaat Ali
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Nescolarde-Selva, Josué Antonio|||/items/bd921352-9e91-44d9-a574-4587b28566ba
Modeling animal decision-making requires mathematical rigor and computational analysis to capture underlying cognitive mechanisms. This study presents a cognitive model for rat decision-making behavior in T-mazes by combining stochastic methods with deep neural architectures. The model adapts Wyckoff’s stochastic framework, originally grounded in Bush’s discrimination learning theory, to describe probabilistic transitions between directional choices under reinforcement contingencies. The existence and uniqueness of solutions are demonstrated via fixed-point theorems, ensuring the formulation is well-posed. The asymptotic properties of the system are examined under boundary conditions to understand the convergence behavior of decision probabilities across trials. Empirical validation is performed using Monte Carlo simulations to compare expected trajectories with the model’s predictive output. The dataset comprises spatial trajectory recordings of rats navigating toward food rewards under controlled experimental protocols. Trajectories are preprocessed through statistical filtering, augmented to address data imbalance, and embedded using t-SNE to visualize separability across behavioral states. A hybrid convolutional-recurrent neural network (CNN-LSTM) is trained on these representations and achieves a classification accuracy of 82.24%, outperforming conventional machine learning models, including support vector machines and random forests. In addition to discrete choice prediction, the network reconstructs continuous paths, enabling full behavioral sequence modeling from partial observations. The integration of stochastic dynamics and deep learning develops a computational basis for analyzing spatial decision-making in animal behavior. The proposed approach contributes to computational models of cognition by linking observable behavior to internal processes in navigational tasks.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Integrating Subjectivity Analysis for Disinformation Detection in Spanish

  • Pérez Montero, Alba
  • Pérez Montero, Alba|||/items/933a3a2a-82b5-4d6e-9337-2e478a6c3f42
The widespread availability of internet access has revolutionized information consumption and creation, as evidenced by high online engagement in Spain. However, this digital scene also promotes the propagation of disinformation driven by ideological and economic motivations. This research undertakes a comprehensive analysis of subjectivity-related linguistic cues to identify textual features that can differentiate deceptive content. Adopting an integrative perspective, this study address disinformation, which is misleading information designed, presented and promoted to intentionally cause public harm or for profit. In this study we focus on analyzing its pragmatic dimension, manifested in linguistic choices conveying author’s imprint. This has been explored within psychological research though the study of deception, but its specific linguistic expression in the creation of disinformation remains a underexplored area. A more profound understanding of this pragmatic component of disinformation promises to enhance detection models by capturing the intentional manipulation inherent in such content. We argue that the way information is presented is more critical than the content itself in disinformation, contrasting with the traditional objective aspiration of news reporting. Our methodology employs a multidisciplinary approach, integrating analytical and empirical techniques to investigate this phenomenon. The anticipated impact of this research is to significantly improve the ability to recognize deceptiveness in written Spanish news through the analysis of subjectivity markers.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Bias mitigation for fair automation of classification tasks

  • Consuegra-Ayala, Juan Pablo
  • Gutiérrez, Yoan
  • Almeida-Cruz, Yudivian
  • Palomar, Manuel
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Consuegra-Ayala, Juan Pablo|||/items/5a98e4ca-607f-4aa0-91c2-a5d929bab52c
The incorporation of machine learning algorithms into high-risk decision-making tasks has raised some alarms in the scientific community. Research shows that machine learning-based technologies can contain biases that cause unfair decisions for certain population groups. The fundamental danger of ignoring this problem is that machine learning methods can not only reflect the biases present in our society but could also amplify them. This article presents the design and validation of a technology to assist the fair automation of classification problems. In essence, the proposal is based on taking advantage of the intermediate solutions generated during the resolution of classification problems through using Auto-ML tools, in particular, AutoGOAL, to create unbiased/fair classifiers. The technology employs a multi-objective optimization search to find the collection of models with the best trade-offs between performance and fairness. To solve the optimization problem, we introduce a combination of Probabilistic Grammatical Evolution Search and NSGA-II. The technology was evaluated using the Adult dataset from the UCI repository, a common benchmark in related research. Results were compared with other published results in scenarios with single and multiple fairness definitions. Our experiments demonstrate the technology's ability to automate classification tasks while incorporating fairness constraints. Additionally, our method achieves competitive results against other bias mitigation techniques. A notable advantage of our approach is its minimal requirement for machine learning expertise, thanks to its Auto-ML foundation. This makes the technology accessible and valuable for advancing fairness in machine learning applications. The source code is available online for the research community.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Analysing the Problem of Automatic Evaluation of Language Generation Systems, Analizando el Problema de la Evaluación Automática de los Sistemas de Generación de Lenguaje

  • Martínez-Murillo, Iván
  • Moreda, Paloma
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
Automatic text evaluation metrics are widely used to measure the performance of a Natural Language Generation (NLG) system. However, these metrics have several limitations. This article empirically analyses the problem with current evaluation metrics, such as their lack of ability to measure the semantic quality of a text or their high dependence on the texts they are compared against. Additionally, traditional NLG systems are compared against more recent systems based on neural networks. Finally, an experiment with GPT-4 is proposed to determine if it is a reliable source for evaluating the validity of a text. From the results obtained, it can be concluded that with the current automatic metrics, the improvement of neural systems compared to traditional ones is not so significant. On the other hand, if we analyse the qualitative aspects of the texts generated, this improvement is reflected.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Multidimensional Data Analysis for Enhancing In-Depth Knowledge on the Characteristics of Science and Technology Parks

  • Francés, Olga
  • Abreu Salas, José Ignacio
  • Fernández Martínez, Javier
  • Gutiérrez, Yoan
  • Palomar, Manuel
  • Abreu Salas, José Ignacio|||/items/99fd9ec6-0b97-4c02-a28e-98bc309cff48
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Francés, Olga|||/items/174da0ee-29c0-4901-a69c-cfe706e01dce
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
The role played by science and technology parks (STPs) in technology transfer, industrial innovation, and economic growth is examined in this paper. The accurate monitoring of their evolution and impact is hindered by the lack of uniformity in STP models or goals, and the scarcity of high-quality datasets. This work uses existing terminologies, definitions, and core features of STPs to conduct a multidimensional data analysis that explores and evaluates the 21 core features which describe the key internal factors of an STP. The core features are gathered from a reliable and updatable dataset of Spanish STPs. The methodological framework can be replicated for other STP contexts and is based on descriptive techniques and machine-learning tools. The results of the study provide an overview of the general situation of STPs in Spain, validate the existence and characteristics of three types of STPs, and identify the typical features of STPs. Moreover, the prototype STP can be used as a benchmark so that other STPs can identify the features that need to be improved. Finally, this work makes it possible to carry out classifications of STPs, in addition to prediction and decision making for innovation ecosystems.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Detección y clasificación del fenómeno de la "alucinación" en textos generados automáticamente

  • Madrigal Cutillas, Jairo
Este TFG propone el diseño y desarrollo de un método que permita el análisis del grado de alucinación que contiene un texto generado de forma automática. Para ello, se utilizarán técnicas y recursos de Inteligencia Artificial y Procesamiento de Lenguaje Natural (PLN), en concreto técnicas automáticas que permitan analizar el texto a distintos niveles y extraer y descubrir información de manera automática, con la finalidad de detectar la alucinación existente y clasificarla según su tipo.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Conscious Natural Text Generation

  • Lloret, Elena
  • Suárez Cueto, Armando
  • Ferrández, Antonio
  • Martin, Tania Josephine
  • Martínez-Murillo, Iván
  • Miró Maestre, María
  • Moreda, Paloma
  • Navarro Colorado, Borja
  • Palomar, Manuel
  • Ferrández, Antonio|||/items/b77d3a3a-c05b-4aa1-921f-a0f269e50ba1
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martin, Tania Josephine|||/items/58bfb24e-52da-4c1b-a00c-21281177e278
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Navarro Colorado, Borja|||/items/e3aa6827-9508-46f7-833a-2f084cd5e24a
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Suárez Cueto, Armando|||/items/63f12a3d-4bd9-4c83-b056-383e1645a62d
  • Miró Maestre, María|||/items/54fede9e-4116-446d-b668-9871db0ac7f3
The “Conscious Natural Text Generation” project (CORTEX, grant ref. PID2021-123956OB-I00) investigates how Natural Language Generation (NLG) architectures can be improved so that they can exploit external and commonsense knowledge, and integrate it in a controllable manner (i.e., determining what knowledge to include and how to include it) when generating new text. Our main scientific objective is, therefore, to investigate and propose novel NLG architectures that integrate different types of knowledge to automatically produce reliable, truthful and quality texts, whose information complies with the principles of objectivity and plurality, thereby minimizing bias or manipulated content. The new generation of NLG systems obtained from CORTEX will significantly improve the semantic quality of the generated text, preventing, among other phenomena, the inclusion of invented facts that do not match reality (i.e., hallucination).
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

To Write or Not to Write as a Machine? That’s the Question

  • Sepúlveda-Torres, Robiert
  • Martínez-Murillo, Iván
  • Saquete Boró, Estela
  • Lloret, Elena
  • Palomar, Manuel
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Martínez-Murillo, Iván|||/items/10185dd6-7baf-4c77-9241-9ca9c38f31a1
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
Considering the potential of tools such as ChatGPT or Gemini to generate texts in a similar way to a human would do, having reliable detectors of AI –AI-generated content (AIGC) is vital to combat the misuse and the surrounding negative consequences of those tools. Most research on AIGC detection has focused on the English language, often overlooking other languages that also have tools capable of generating human-like texts, such is the case of the Spanish language. This paper proposes a novel multilingual and multi-task approach for detecting machine vs. human-generated text. The first task classifies whether a text is written by a machine or by a human, which is the research objective of this paper. The second task consists in detect the language of the text. To evaluate the results of our approach, this study has framed the scope of the AuTexTification shared task and also we have collected a different dataset in Spanish. The experiments carried out in Spanish and English show that our approach is very competitive concerning the state of the art, as well as it can generalize better, thus being able to detect an AI-generated text in multiple domains.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Leveraging relevant summarized information and multi-layer classification to generalize the detection of misleading headlines

  • Sepúlveda-Torres, Robiert
  • Vicente, Marta
  • Saquete Boró, Estela
  • Lloret, Elena
  • Palomar, Manuel
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
Disinformation is an important problem facing society nowadays. Given the rapid and easy access to information, news stories quickly go viral, the vast majority of which are misleading and with no prospect of verification. Specifically, the headline of a correctly designed news item must correspond to a summary of the main information of that news item and it should be neutral. However, many headlines circulating on the Internet use false or distorted information, seeking to confuse or mislead the reader. Misleading headlines indicate a dissonance between the headline and the content of the news story. From a computational perspective, this problem is being tackled as a Stance Detection problem between the headline and the body text of the news item. This paper contributes to the fight against the spread of misleading information by presenting a generic and flexible multi-level hierarchical classification. The approach is based on two stages that enable the detection of the stance between the news headline and the body text. The proposed architecture, called HeadlineStanceChecker+ uses the headline and only the essential information of the news item (not the full body text) as inputs. To extract this essential information, different summarization approaches (extractive and abstractive) are analyzed in order to determine the most relevant information for the task. The experimentation has been carried out using the Fake News Challenge (FNC-1) dataset. A 94.49% accuracy was obtained using extractive summaries, which were more helpful than abstractive ones. HeadlineStanceChecker+ improves the accuracy results of existing state-of-the-art systems. In conclusion, using automatic extractive summaries together with the two-stage generic architecture is an effective solution to the problem.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A Comprehensive Review of AI and Human Language Technologies for Data-Driven Fashion Trend Forecasting

  • Villalba, María
  • Palomar, Manuel
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
This review examines the integration of Human Language Technologies (HLT) and Artificial Intelligence (AI) in the field of fashion trend prediction. It highlights how methodologies such as Natural Language Processing (NLP), Machine Learning (ML), and Deep Learning (DL) support trend forecasting through the analysis of heterogeneous data sources, including text, images, and social interactions. Based on the analysis of a curated set of 30 research articles, the review identifies the most commonly adopted technologies, including time-series models, Graph Neural Networks (GNNs), and regression-based approaches. In addition, key challenges in AI-driven fashion trend prediction, particularly those related to data bias and inclusivity, are discussed, emphasizing the need for more representative and diverse datasets. Overall, this review provides an overview of current technological trends and offers a basis for future research on fashion trend prediction in design contexts.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Mitigación de Sesgos para la Automatización Justa de Tareas de Clasificación

  • Consuegra-Ayala, Juan Pablo
  • Consuegra-Ayala, Juan Pablo|||/items/5a98e4ca-607f-4aa0-91c2-a5d929bab52c
Los modelos de aprendizaje automático están siendo ampliamente utilizados en múltiples áreas de la vida humana. Tradicionalmente, se han aplicado en reconocimiento de voz, detección de rostros, clasificación de imágenes, sistemas de recomendación, etc. Con la reciente revolución de los modelos generativos, la popularidad de los chatbots conversacionales se ha disparado. Esto ha dado lugar a que los modelos de aprendizaje automático se utilicen cada vez más para abordar tareas para las que no estaban específicamente capacitados. El prompt engineering ha permitido que personas no expertas en aprendizaje automático (que comúnmente tampoco están familiarizadas con los problemas subyacentes al uso de modelos de aprendizaje automático para hacer predicciones) automaticen ciertas tareas. La incorporación de algoritmos de aprendizaje automático en tareas de toma de decisiones de alto riesgo ha levantado algunas alertas en la comunidad científica. Las tareas de toma de decisiones de alto riesgo denotan aquellas tareas que pueden tener un gran impacto en las vidas de las personas sobre quienes se toman las decisiones. Por ejemplo, se han utilizado modelos para decidir si una persona es contratada o no, si se le concede un préstamo, si se acepta una solicitud de cobertura ampliada de seguridad sanitaria y para predecir la probabilidad de reincidencia en un delito. Estudios han demostrado que la automatización inconsciente de este tipo de tareas contiene sesgos, lo cual provoca que decisiones injustas sean tomadas sobre determinados grupos de población. El peligro fundamental de ignorar este problema es que los métodos de aprendizaje automático podrían no sólo reflejar los sesgos presentes en nuestra sociedad, sino que también amplificarlos. Esta tesis presenta el diseño y validación de una tecnología para asistir la automatización justa de problemas de clasificación. En esencia, la propuesta se basa en diseñar una tecnología que saque provecho de las soluciones intermedias generadas durante la resolución de problemas de clasificación mediante el uso de herramientas de Auto-ML, en particular, AutoGOAL, con el propósito de crear clasificadores imparciales y justos. Cuatro componentes fundamentales conforman la propuesta: (I) una componente de Auto-ML, encargada de generar colecciones de modelos con hipótesis diferentes entre sí, cada uno debiendo ser capaz de transformar los datos de entrada a los de salida; (II) una componente de ensemble, responsable de combinar múltiples soluciones para producir una más robusta, exacta y justa, según criterios definidos por funciones de pérdida; (III) una componente de cuantificación de sesgos, encargada de medir la calidad de un modelo según varias definiciones de sesgo y equidad; y (IV) una componente de anotación automática de atributos protegidos, para permitir estimar los sesgos en situaciones donde normalmente no sería posible. Los resultados discutidos en este documento prueban la capacidad de la tecnología propuesta para automatizar tareas de clasificación a la par que se controla su equidad. Además, la experimentación muestra la competitividad de la propuesta respecto a otras alternativas para controlar los sesgos en el modelo de aprendizaje automático y colecciones de datos. La propuesta tiene la ventaja adicional de requerir poco o ningún conocimiento sobre arquitecturas de aprendizaje automático dada las componentes de Auto-ML que incorpora. Todo esto lo convierte en una tecnología valiosa y conveniente de explotar. Más allá de los resultados obtenidos sobre la línea principal de investigación, se obtuvieron algunos resultados secundarios de gran valor. Por un lado, se pudo demostrar que ciertas componentes de la tecnología pueden utilizarse para extender, de forma más robusta, corpus de texto con entidades y relaciones anotadas, asumiendo que se cuente con varias versiones de anotación que se quieran combinar; esta condición suele ser viable dada la existencia de competencias internacionales donde varios participantes compiten por generar la mejor solución. Muy ligado a esto, otro resultado secundario es la generación del eHealth-KD 2019 ensembled corpus a partir de ensamblar las soluciones participantes de la competencia eHealth-KD 2019. Otro resultado secundario se tiene en la componente de anotación automática de atributos protegidos, la cual puede funcionar independiente del flujo end-to-end de automatización justa, y por tanto puede utilizarse como fase de preprocesamiento para otros sistemas de cuantificación o mitigación de sesgos. En ese sentido, se publicó también el corpus Reviews' Gender} diseñado para auxiliar el entrenamiento y evaluación de modelos de anotación de atributos protegidos con el fin de usar sus predicciones como estimadores de equidad. Todos los recursos desarrollados en esta investigación están a disposición pública de la comunidad científica.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

El lenguaje figurado en los LLM: Evaluación y análisis, Figurative Language in LLMs: Evaluation and Analysis

  • Ramírez Trives, Marta
  • Lloret, Elena
  • Bonet-Jover, Alba
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Bonet-Jover, Alba|||/items/6bd6e7a1-46a7-415c-bdde-2a1e56f97a2f
Pese a los avances en Procesamiento del Lenguaje Natural (PLN), el lenguaje figurado sigue siendo un reto para los grandes modelos de lenguaje (LLM). En este estudio evaluamos y comparamos el rendimiento de los LLM ChatGPT-4o, DeepSeek- V3, Gemini 2.5 Pro Experimental y Grok 3 Preview en tareas de procesamiento del lenguaje figurado. Basándonos en la teoría del lenguaje figurativo convencional (CFLT) de Dobrovol’skij y Piirainen (2021), compilamos CLUE, un conjunto de datos inglés-español de metáforas, modismos, símiles y proverbios. A partir de él, diseñamos y llevamos a cabo pruebas de detección, interpretación y generación de lenguaje figurado. Los modelos ofrecieron resultados excelentes en detección (0,94) e interpretación (0,91) en ambas lenguas. Sin embargo, exceptuando a Gemini, su rendimiento bajó notablemente en la prueba de generación (0,70), especialmente en español. Concluimos que los LLM son eficaces en tareas de comprensión del lenguaje figurado, pero su capacidad para producirlo es más limitada.