Pasar al contenido principal

TECNOLOGIAS DEL LENGUAJE HUMANO PARA ENTIDADES DIGITALES VIVAS

RTI2018-094653-B-C21

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE JAEN

Resultados relacionados

Resultados totales (Incluyendo duplicados): 16
Encontrada(s) 1 página(s)

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

The Disinformation Battle: Linguistics and Artificial Intelligence Join to Beat it, La Batalla de la Desinformación: la Lingüística y la Inteligencia Artificial se Unen para Vencerla

  • Bonet-Jover, Alba
  • Bonet-Jover, Alba|||/items/6bd6e7a1-46a7-415c-bdde-2a1e56f97a2f
At present, the era of digitalisation has led to the era of disinformation by witnessing a peak of the spreading of fake news that are disseminated in order to get profit. Like everything, fake news has an Achilles' heel and it could be language. The linguistic structure as well as the expression of emotions through language could be key in detecting deception. The modelling of a language of deception typical of fake news and its later automation through machine learning would allow to take a further step towards the fight against disinformation.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Exploiting discourse structure of traditional digital media to enhance automatic fake news detection

  • Bonet-Jover, Alba
  • Piad-Morffis, Alejandro
  • Saquete Boró, Estela
  • Martínez-Barco, Patricio
  • García Cumbreras, Miguel Ángel
  • Bonet-Jover, Alba|||/items/6bd6e7a1-46a7-415c-bdde-2a1e56f97a2f
  • Martínez-Barco, Patricio|||/items/f9630270-fe31-44c8-b611-dfaf9c109a4d
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
This paper presents a novel architecture for dealing with Automatic Fake News detection. The architecture factors in the discourse structure of news in traditional digital media and is based on two premises. First, fake news tends to mix true and false information with the purpose of confusing readers. Second, this research is focused on fake news delivered in traditional digital media, so our approach considers the influence of the journalistic structure of news, and the way journalists tend to introduce the essential content in a news story using 5W1H answer. Considering both premises, this proposal deals with the news components separately because some may be true or false, instead of considering the veracity value of the news article as a unit. A two-layer architecture is proposed, Structure and Veracity layers. To demonstrate the validity of the proposal, a new dataset was created and annotated with a new fine-grained annotation scheme (FNDeepML) that considers the different elements of the news document and their veracity. Due to the severity of the COVID-19 pandemic crisis, health is the chosen domain, and Spanish is the language used to validate the architecture, given the lack of research in this language. However, the proposal can be applied to any other language or domain. The performance of the Veracity layer of our proposal, which factors in the traditional news article structure and the 5W1H annotation, is capable of delivering a result of F1=0.807. This represents a strong improvement when compared to the baseline, which uses the whole document with a single veracity value, obtaining F1=0.605. These findings validate the suitability and effectiveness of our approach.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

“Here Are the Rules: Ignore All Rules”: Automatic Contradiction Detection in Spanish

  • Sepúlveda-Torres, Robiert
  • Bonet-Jover, Alba
  • Saquete Boró, Estela
  • Bonet-Jover, Alba|||/items/6bd6e7a1-46a7-415c-bdde-2a1e56f97a2f
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
This paper tackles automatic detection of contradictions in Spanish within the news domain. Two pieces of information are classified as compatible, contradictory, or unrelated information. To deal with the task, the ES-Contradiction dataset was created. This dataset contains a balanced number of each of the three types of information. The novelty of the research is the fine-grained annotation of the different types of contradictions in the dataset. Presently, four different types of contradictions are covered in the contradiction examples: negation, antonyms, numerical, and structural. However, future work will extend the dataset with all possible types of contradictions. In order to validate the effectiveness of the dataset, a pretrained model is used (BETO), and after performing different experiments, the system is able to detect contradiction with a F1m of 92.47%. Regarding the type of contradictions, the best results are obtained with negation contradiction (F1m = 98%), whereas structural contradictions obtain the lowest results (F1m = 69%) because of the smaller number of structural examples, due to the complexity of generating them. When dealing with a more generalistic dataset such as XNLI, our dataset fails to detect most of the contradictions properly, as the size of both datasets are very different and our dataset only covers four types of contradiction. However, using the classification of the contradictions leads us to conclude that there are highly complex contradictions that will need external knowledge in order to be properly detected and this will avoid the need for them to be previously exposed to the system.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Overview of the EmoEvalEs task on emotion detection for Spanish at IberLEF 2021, Resumen de la tarea de detección de emociones en español EmoEvalEs en IberLEF 2021

  • Plaza-del-Arco, Flor Miriam
  • Jiménez Zafra, Salud M.
  • Montejo Ráez, Arturo
  • Molina González, M. Dolores
  • Ureña López, Luis Alfonso
  • Martín Valdivia, María Teresa
This paper presents the EmoEvalEs shared task, organized at IberLEF 2021, as part of the 37th International Conference of the Spanish Society for Natural Language Processing (SEPLN 2021). The aim of this task is to promote the Emotion detection and Evaluation for Spanish. It consists of a fine-grained emotion classification of tweets from the EmoEvalEs corpus in one of these seven classes: anger, disgust, fear, joy, sadness, surprise, or others. In this edition, 70 teams registered, 15 submitted results and 11 presented papers describing their systems. Most teams experimented with neural networks, being Transformers the most widely used model. It should be noted that few of them also considered the features of offensiveness and event that were provided in the corpus apart from the tweet texts.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Negation Processing in Spanish and its Application to Sentiment Analysis, Tratamiento de la Negación en Español y su Aplicación al Análisis de Sentimientos

  • Jiménez Zafra, Salud M.
This is a summary of the Ph.D. thesis written by Salud María Jiménez Zafra at Universidad de Jaén under the supervision of Ph.D. María Teresa Martín Valdivia and Ph.D. L. Alfonso Ureña López. The author was examined on Friday, September 13th, 2019 by a committee formed by Ph.D. Ruslan Mitkov from the University of Wolverhampton, Ph.D. Miguel Ángel García Cumbreras from Universidad de Jaén and Ph.D. Eugenio Martínez Cámara from Universidad de Granada. The Ph.D. thesis obtained Summa Cum Laude and the international mention. Moreover, it was awarded as the best thesis in Natural Language Processing at the 36th International Conference of the Spanish Society for Natural Language Processing (SEPLN 2020).
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Automatic Contradiction Detection in Spanish

  • Sepúlveda-Torres, Robiert
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
This paper addresses the lack of automated contradiction detection systems for the Spanish language. The ES-Contradiction dataset was created and contains examples with two pieces of information classified as Compatible, Contradiction, or Unrelated. To the author’s knowledge, a Spanish-language contradiction dataset is non-existent and therefore, the ES-Contradiction dataset fills an important research gap, given Spanish being one of the most widely spoken languages. Moreover, the dataset built includes a fine-grained annotation of the different types of contradictions in the dataset. A baseline system was designed to validate the effectiveness of the dataset. The BETO transformer model was used to build this baseline system, which obtained a good result to detect the three class labels Compatible, Contradiction, or Unrelated.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Semi-automatic Annotation Proposal for Increasing a Fake News Dataset in Spanish

  • Bonet-Jover, Alba
  • Bonet-Jover, Alba|||/items/6bd6e7a1-46a7-415c-bdde-2a1e56f97a2f
The digital era has become an ally of fake news, since it has increased the spread and amount of false information. Fake news is a global problem that causes disorder and generates fear. This phenomenon must be attacked in the same environment in which it is generated: in the digital environment. This paper presents the current state of my doctoral thesis which focuses on the linguistic modelling applied to the automatic detection of fake news through Natural Language Processing (NLP). In order to study the linguistic characteristics of fake news and to create computational models that automate its detection, labelled datasets are needed, but this is a costly task that requires time and expertise. A fake news dataset and an annotation guide were created ad hoc in a previous work to analyse all the parts and elements of a news item. However, after creating and training our system, we realised that the time spent was not proportional to the low annotated data obtained. The need of creating a larger corpus to train and test our hypothesis has led us to think about a way of increasing our corpus without spending so much time. For that purpose, a semi-automatic annotation is proposed for reducing time while increasing speed and quantity of the examples annotated. This proposal, besides allowing us to make progress in our research, may facilitate the creation of datasets, which are essential in NLP research.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Why are some social-media contents more popular than others? Opinion and association rules mining applied to virality patterns discovery

  • Saquete Boró, Estela
  • Zubcoff, Jose
  • Gutiérrez, Yoan
  • Martínez-Barco, Patricio
  • Fernández Martínez, Javier
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Martínez-Barco, Patricio|||/items/f9630270-fe31-44c8-b611-dfaf9c109a4d
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Zubcoff, Jose|||/items/c8d086dc-e561-4ce4-9d9b-2db5c48a75f5
Discovering the main features of virality patterns in Twitter is the focus of this research. Five trending topics related to the COVID-19 pandemic were selected for the study, with Spanish as the target language. To carry out the discovery of virality patterns, we applied opinion mining techniques that enable us to structure the information based on the polarity of the messages and the emotions they contain. After transforming the information from an unstructured textual representation to a structured one, data mining techniques were applied, specifically association rules mining. Message patterns with the highest virality (high shares and high likes), and at the same time the most relevant characteristics of the patterns with less impact were extracted. After an exhaustive analysis of the most relevant non-redundant rules, it can be concluded that messages with a high-negative polarity and a very high emotional charge, especially emotions that have intensified with the COVID-19 pandemic, such as fear, sadness, anger and surprise are more likely to go viral in social media. By contrast, messages with little news coverage in the media, few authors, and the absence of surprise are relevant features when it comes to seeing messages with very low dissemination in social media.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Biomedical entities recognition in Spanish combining word embeddings, Reconocimiento de entidades biomédicas en español combinando word embedding

  • López-Úbeda, Pilar
This is a summary of the Ph.D. thesis written by Pilar López Úbeda at Universidad de Jaén under the supervision of PhD. M. Teresa Martín Valdivia, Ph.D. L. Alfonso Ureña López and PhD. Manuel Carlos Díaz Galiano. The defense was held in Jaén on April 22, 2021. The doctoral committee was integrated by PhD. Rafael Muñoz Guillena from Universidad de Alicante, PhD. Paloma Martínez Fernández from Universidad Carlos III de Madrid, and Manuel Montes y Gómez from National Institute of Astrophysics, Optics and Electronics (Mexico). The thesis obtained the grade of Summa Cum Laude and the international mention.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

NECOS: An annotated corpus to identify constructive news comments in Spanish, NECOS: Un corpus anotado para identificar comentarios constructivos de noticias en español

  • López-Úbeda, Pilar
  • Plaza-del-Arco, Flor Miriam
  • Díaz Galiano, Manuel Carlos
  • Martín Valdivia, María Teresa
In this paper, we present the NEws and COmments in Spanish (NECOS) corpus, a collection of Spanish comments posted in response to newspaper articles. Following a robust annotation scheme, three annotators labeled the comments as constructive and non-constructive. The articles were published in the newspaper El Mundo between April 3rd and April 30th, 2018. The corpus is composed of a total of 10 news articles and 1,419 comments. Three annotators manually labeled NECOS with an average Cohen's kappa of 78.97. Our current focus is the study of constructiveness and the evaluation of the Spanish NECOS corpus. In order to address this goal, we propose a benchmark testing different machine learning systems based on Natural Language Processing: a traditional system and the novel Transformer-based models. Specifically, we compare multilingual models with a monolingual model trained on Spanish in order to highlight the need to create resources trained on a specific language. The monolingual model fine-tuning on NECOS obtain the best result by achieving a macro-average F1 score of 77.24%.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

LIVING-LANG: Living digital entities by human language technologies, LIVING-LANG: Tecnologías del lenguaje humano para entidades digitales vivas

  • Ureña López, Luis Alfonso
  • Saquete Boró, Estela
  • Martín Valdivia, María Teresa
  • Martínez-Barco, Patricio
  • Martínez-Barco, Patricio|||/items/f9630270-fe31-44c8-b611-dfaf9c109a4d
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
This project pursues the dynamic modeling at a spatial-temporal level of digital entities in social media for predicting their behavior. Firstly, digital entities are modelled by identifying the characteristics of individuals through their language and footprint on the network. Then, the extraction of relationships between digital entities is one of the nuclear challenges of the project. The proposal pursues this objective on a semantic level, structuring the information into representations of knowledge suitable for logical processing. Considering the heterogeneous nature of the sources to be dealt with, filtering of information is fundamental, using metrics and quality criteria. This spatial-temporal characterization, together with screening processes, will allow us to study high-performance predictive strategies in the evolution of digital entities. This project is coordinated by the SINAI and GPLSI research groups.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Detección de información engañosa mediante Tecnologías del Lenguaje Humano e Inteligencia Artificial

  • Sepúlveda-Torres, Robiert
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
En los últimos años, el consumo de noticias en medios impresos ha sido sustituido en gran medida por el acceso a estas en variados formatos a través de medios digitales y redes sociales. Los bajos costes de acceso a la información y la profusión de las plataformas de comunicación y dispositivos móviles han producido un cambio en los hábitos de consumo de información, la que es recibida desde múltiples fuentes y replicada con inmediatez en un ambiente global. En este contexto, se ha incrementado la desinformación, un problema originado en los albores de la prensa tradicional. En la última década, la desinformación ha alcanzado una escala inmanejable debido al gran volumen de información al que un ciudadano común está expuesto cada día. A esto se suma que la mayoría de estos medios digitales no son arbitrados, y permiten publicar y compartir cualquier tipo de información. En este ambiente es muy probable la proliferación de información engañosa que, en la mayoría de los casos, pretende influir en la opinión pública para perseguir un objetivo económico, social o político subyacente. Esto puede perjudicar a las organizaciones, a las marcas y a las personas, entre otros, derivando en muchas ocasiones en conclusiones precipitadas por parte de los usuarios que la consumen. En este contexto surge el término de la posverdad como una tendencia a priorizar la subjetividad de una interpretación a la verificación de hechos reales. El titular de una noticia está diseñado para resumir sucintamente su contenido, proporcionando al lector una comprensión clara de la misma. Desafortunadamente, en la era de la posverdad, los titulares están más enfocados en atraer la atención del lector que en presentar con precisión el contenido de la noticia. Esto abre una enorme oportunidad para difundir desinformación con la construcción de titulares falsos o distorsionados. Las técnicas tradicionales de verificación de hechos realizadas por humanos son definitivamente impracticables y obsoletas ante la cantidad de textos informativos que se generan incluso cada hora. En este trabajo se abordan soluciones novedosas utilizando Tecnologías de Lenguaje Humano (TLH) y técnicas de Inteligencia Artificial (IA). Esta investigación se ha desarrollado en un área donde se intersecan confusamente diferentes conceptos, herramientas y aproximaciones. Se parte de una ubicación en el estado del arte acerca de las principales soluciones relacionadas con la detección de titulares engañosos, detección de posturas, detección de contradicciones, interrelación entre estos elementos y verificación automática de hechos. A partir del problema enunciado y sus conceptos, se profundiza en diferentes estrategias de solución con la aspiración de proponer una aproximación que permita, con un enfoque suficientemente práctico, aportar a la detección de información engañosa en medios digitales lo que puede convertirse en una herramienta de alerta en el complejo ambiente antes descrito. Entre los elementos considerados, se valora la utilización de ML y de DL como técnicas tradicionales de trabajo en el espacio de estas soluciones, así como sus alcances y limitaciones. Además, se introduce la idea de sustituir el contenido de una noticia por un resumen suficientemente esencial y obtenido de manera automática. La memoria presenta de manera lógica el curso de la investigación que parte de lo conceptual y utiliza el pensamiento deductivo y experimental para alcanzar generalizaciones y aplicarlas deductivamente a la solución de problemas específicos. Con ello, se abordan determinadas tareas que pueden contribuir parcialmente a la solución de parte del problema planteado, se diseñan experimentos y se especifica la solución en el ámbito del idioma español donde no se reportan aportaciones similares. Se propone una arquitectura flexible para la detección de titulares engañosos que ha permitido implementar sobre ella dos prototipos cuyos resultados experimentales y documentados suponen un paso de avance hacia la automatización de esta tarea. Esta arquitectura alcanza resultados notables al ser aplicada sobre dos conjuntos de datos en idioma inglés y español. Siguiendo los principios y las experiencias adquiridas se presenta una aplicación de una arquitectura similar para la detección de noticias falsas, lo que hace presumir su posible generalidad.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Overview of MeOffendEs at IberLEF 2021: Offensive Language Detection in Spanish Variants, Resumen de la tarea MeOffendEs en IberLEF 2021: Detección de lenguaje ofensivo en las variantes del español

  • Plaza-del-Arco, Flor Miriam
  • Casavantes, Marco
  • Escalante, Hugo Jair
  • Martín Valdivia, María Teresa
  • Montejo Ráez, Arturo
  • Montes y Gómez, Manuel
  • Jarquín-Vásquez, Horacio
  • Villaseñor Pineda, Luis
This paper is an overview of MeOffendES 2021, organized at IberLEF 2021 and co-located with the 37th International Conference of the Spanish Society for Natural Language Processing (SEPLN 2021). The main purpose of MeOffendEs is to promote research on the detection of offensive language in Spanish variants. The shared task involve four subtasks, the first two correspond to the identification of offensive language categories in generic Spanish texts from different social media platforms, while subtasks 3 and 4 are related to the identification of offensive language targeting the Mexican variant of Spanish. Two annotated datasets on offensive language have been released to the Natural Language Processing community. MeOffendes attracted a large number of participants: a total of 69 signed up to participate in the task, 12 submitted official runs on the test data, and 10 submitted system description papers. Corpora and results are available at the shared task website at https://competitions.codalab.org/competitions/28679.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

The Text Complexity Library, Biblioteca de Complejidad Textual

  • López-Anguita, Rocío
  • Collado-Montañez, Jaime
  • Montejo Ráez, Arturo
This paper introduces a new resource for computing textual complexity. It consists in a Python library for calculating different complexity metrics for several languages from plain texts. The resource has been made available to the research community and provides all needed instructions for its installation and use. To our knowledge, it is the first time a resource like this is published, so we expect many researchers can profit from it.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Overview of PoliticEs 2022: Spanish Author Profiling for Political Ideology, Resumen de la tarea PoliticEs 2022: Perfilado del Autor Español por su Ideología Política

  • García-Díaz, José Antonio
  • Jiménez Zafra, Salud M.
  • Martín Valdivia, María Teresa
  • García-Sánchez, Francisco
  • Ureña López, Luis Alfonso
  • Valencia García, Rafael
This paper presents the PoliticEs 2022 shared task, organized at IberLEF 2022 workshop, within the framework of the 38th International Conference of the Spanish Society for Natural Language Processing. This task aims to extract the political ideology from a given user’s set of tweets. Specifically, it focused on the identification of the gender and the profession, as demographic traits, and the political ideology from a binary and multi-class perspective, as a psychographic trait. The PoliticEs task attracted 63 teams that registered through CodaLab. Finally, 20 submitted results and 14 presented working notes describing their systems. Most of the teams proposed transformer-based approaches, although some of them also used traditional machine learning algorithms or even a combination of both approaches.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

EmoCon: Analizador de Emociones en el Congreso de los Diputados, EmoCon: Emotions Analyzer in the Spanish Congress

  • Jiménez Zafra, Salud M.
  • García Cumbreras, Miguel Ángel
  • Martín Valdivia, María Teresa
  • López-Fernández, Andrea
EmoCon es un prototipo de un analizador de emociones en el Congreso de los Diputados. Su objetivo es analizar el perfil emocional a nivel de sesión parlamentaria y a nivel de cada diputado, a partir de las intervenciones realizadas durante las sesiones parlamentarias que tienen lugar en el Congreso de los Diputados. Para ello, la demo cuenta con tres módulos principales: i) descarga automática de los documentos de las sesiones y extracción de las intervenciones realizadas por cada diputado, ii) análisis de las emociones expresadas a nivel de sesión y a nivel de diputado y, iii) visualización de la información en una aplicación web.