Pasar al contenido principal

GENERACION INTELIGENTE DE TEXTOS

RTI2018-094649-B-I00

•
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 ALICANTE

Resultados relacionados

Resultados totales (Incluyendo duplicados): 31
Encontrada(s) 1 página(s)

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

Atención automatizada a estudiantes en el proceso de matriculación en la Universidad de Alicante, Automatic Students Service in the Enrolment Process at the University of Alicante

  • Moreno, Isabel
  • Gutiérrez, Yoan
  • Montoyo, Andres
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
Esta demo presenta un chatbot diseñado para automatizar la atención a los estudiantes durante el proceso de matrícula en la Universidad de Alicante (UA). Hemos creado un chatbot en la plataforma de mensajería instantánea Telegram mediante tecnologías del lenguaje humano e inteligencia artificial. El principal obstáculo ha sido ofrecer el chatbot en los dos idiomas oficiales de la Comunidad Valenciana, por lo que se ha utilizado traducción automática como componente intermedio. Este chatbot ofrece numerosos beneficios a la UA para el proceso de matriculación, pero destacamos el refuerzo que representa para la atención del estudiante, en términos de reducción de costes y asistencia 24/7. Esta tecnología generará un ambiente de confianza entre la UA y sus potenciales estudiantes.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

GPLSI-UH LETO V1.0: Motor de aprendizaje a través de ontologías, GPLSI-UH LETO V1.0: Learning Engine Through Ontologies

  • Estévez-Velarde, Suilan
  • Piad-Morffis, Alejandro
  • Gutiérrez, Yoan
  • Montoyo, Andres
  • Muñoz, Rafael
  • Almeida-Cruz, Yudivian
  • Palomar, Manuel
  • Valdés Pérez, Daniel Alejandro
  • 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
LETO es un marco de aprendizaje de ontologías diseñado para extraer conocimiento de una variedad de fuentes. Estas fuentes pudieran ser datos estructurados y no estructurados, y de ellas se podrá descubrir, actualizar continuamente, enriquecer e integrar información relevante como parte de un único conocimiento semántico. En la actual versión 1.0 se limita a la extracción de conocimiento desde datos no estructurados, i.e. textos en lenguaje natural, siguiendo el modelo semántico publicado en [EGM2018]. Entre sus funcionalidades está la extracción de entidades y relaciones semánticas desde fuentes textuales; la transformación de esta información en elementos interrelacionados mediante técnicas de agrupamientos; y finalmente generación de ontologías representativas del contenido procesado. Se proporciona un punto de acceso API, y una herramienta visual para la manipulación de procesos y visualización de las ontologías obtenidas [EMA2019].
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

HanaNLG: Sistema de generación de lenguaje híbrido y flexible, HanaNLG: A Flexible Hybrid System for Natural Language Generation

  • Barros, Cristina
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
HanaNLG (Hybrid surfAce realisatioN Approach for Natural Language Generation) es un sistema híbrido para la fase realización capaz de generar automáticamente texto que es fácilmente adaptable a diferentes géneros, dominios y lenguajes. HanaNLG es híbrido porque se basa en el uso de recursos lingüísticos así como en información estadística, a través del uso de Modelos de Lenguaje Factorizados, para construir la salida final. Para generar lenguaje, el sistema propuesto hace uso de estrategias de over-generation y ranking, donde primero se genera un conjunto de frases candidatas para después realizar un ranking donde se seleccione una frase en base a un criterio definido, en nuestro caso, su probabilidad. Además, dado que HanaNLG solo está enfocado en la fase de realización, no tenemos información de los procesos de macroplanificación y microplanificación, para poder guiar la generación en base a un tema concreto, palabras, dominio, etc. Es por ello, que proponemos el concepto de característica semilla. Estas características semillas pueden considerarse objetos abstractos (por ejemplo, fonemas, sentimientos, polaridades, etc.) que guiarán el proceso de generación en relación al vocabulario que la frase generada deba contener. Por consiguiente, el tipo de textos generados por HanaNLG puede ser adaptado a diferentes dominios y también a diferentes objetivos comunicativos (por ejemplo, generación automática de resúmenes). Asimismo, dada la naturaleza de los recursos y técnicas empleadas, nuestro sistema también es fácilmente adaptable a diferentes géneros, dominios y lenguajes. Una descripción más detallada del método completo se puede encontrar en [Barros19, Barros17]., HanaNLG (Hybrid surfAce realisatioN Approach for Natural Language Generation) is a hybrid system for the surface realisation stage capable of automatically generating text which is easily adaptable to different genres, domains and language. HanaNLG is hybrid because the final text is created based on the use of linguistic resources in conjunction with statistical information, through the use of factored language models. In order to generate language, this approach makes use of overgeneration and ranking strategies, where a set of candidate sentences is first generated and then a ranking is performed to select a sentence based on a defined criterion, which, in our case, is the sentence probability. In addition, since HanaNLG is only focused on the surface realisation stage, there is not any information about the macroplanning and microplanning processes, so, to guide the generation on the basis of a specific theme, words, domain, etc., we propose the concept of seed feature. These seed features can be considered as abstract objects (e.g., phonemes, emotions, polarities, etc.) which will guide the generation process in relation with the vocabulary that the generated sentence must contain. Therefore, the text generated by HanaNLG can be adapted to different domains and also to different communicative goals (e.g., automatic summarisation). Likewise, given the nature of the resources and techniques employed, our system is also easily adaptable to different genres, domains and language. A detailed description of the complete approach can be found at [Barros19, Barros17].
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A Discourse-Aware Macroplanning Approach for Text Generation and Beyond

  • Vicente, Marta
El trabajo presentado en esta tesis se ha desarrollado dentro del área de generación de lenguaje natural (GLN), disciplina dedicada a investigar e implementar aplicaciones capaces de producir textos coherentes y comprensibles. Al estudiar el contexto de la disciplina, detectamos una carencia de enfoques que, sin requerir excesivos recursos, incorporasen mecanismos apropiados tanto para aprehender mejor el significado de la entrada, como para proporcionar un resultado más consistente y coherente, cuando la entrada del proceso es un texto conformado como discurso. Nuestra investigación se planteó como una propuesta orientada a subsanar este déficit, de modo que la idea de contribuir a la creación de sistemas de generación más adaptables ha constituido el motor del presente trabajo que, estando profundamente arraigado en el ámbito de la GLN, pretende también beneficiar a otras tareas más orientadas a la comprensión del lenguaje. Dado que el campo de GLN es extremadamente amplio, decidimos abordar un aspecto específico del proceso de generación. Nos centramos principalmente en una parte del proceso responsable de seleccionar y organizar el contenido que debe aparecer en la salida del sistema. Esta fase se conoce generalmente como macroplanificación. El núcleo de esta investigación se basa en la idea de que el proceso de generación debe estar estrechamente ligado, condicionado por el significado que emerge del texto como discurso. Así pues nuestro objetivo principal se centró en la definición de una metodología para la etapa de macroplanificación que, en primer lugar, aprovechara la información semántica y estructural del texto concebido como discurso y, en segundo lugar, permitiera su adaptación a múltiples escenarios (aplicaciones, dominios) sin un requisito elevado de recursos. Siguiendo este planteamiento, la hipótesis inicial de esta investigación establece que la explotación de la información semántica, también determinada por la estructura del discurso, tomada como base para diseñar una metodología de macroplanificación basada en datos (esto es, aprovechando las técnicas estadísticas), puede conducir a sistemas más flexibles, adaptables, equipados adecuadamente para proporcionar textos más coherentes y significativos. Nos alineamos en este sentido con una corriente de investigación que defiende que la incorporación del conocimiento estructural que procede del discurso deviene en una representación del discurso más completa y efectiva. Para lograr nuestro propósito, estudiamos y aplicamos una metodología basada en un tipo de modelos de lenguaje designados como modelos de lenguaje posicionales, capaces de capturar tanto información relevante como posicional. Mediante una serie de experimentos, analizamos su comportamiento y estudiamos cómo variaciones en su configuración nos permitían ejercer cierto control sobre la complejidad estructural de los resultados. Adaptamos la metodología a diferentes dominios y tareas dentro del campo de la GLN: generación de cuentos, creación de resúmenes extractivos y producción de titulares de noticias desde un enfoque abstractivo, con resultados positivos considerando tanto evaluaciones intrínsecas como extrínsecas, humanas y automáticas. Más aún, alejándonos del ámbito de la GLN, en línea con nuestros objetivos iniciales, quisimos comprobar que nuestro enfoque puede contribuir también a otras tareas del ámbito del procesamiento de lenguaje natural. Para ello, adaptamos nuestra metodología a un sistema destinado a detectar y clasificar titulares engañosos, con resultados que demuestran la conveniencia de emplear los principios establecidos a lo largo de la tesis para la resolución de la tarea de detección de postura o posicionamiento. Las posibilidades de aplicación de nuestro planteamiento son muy diversas y entrañan diferentes niveles de complejidad. Y si bien en el transcurso de nuestra investigación hemos detectado un número de limitaciones, también hemos identificado potenciales desarrollos. Ambos aspectos constituyen el núcleo de esta tesis y conforman la semilla de nuestros planes futuros, pues señalan nuevas fronteras para nuestro trabajo incluyendo, entre otras, la aplicación del enfoque presentado a diferentes lenguajes, la profundización en la dimensión pragmática del discurso y su incorporación, la hibridación de los modelos de lenguaje empleados con técnicas basadas en aprendizaje profundo o la incorporación de la metodología a otras tareas de comprensión del lenguaje, como la inferencia, la implicación textual o la búsqueda de respuestas.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Social-Univ 2.0: Monitorización del entorno digital social universitario, Social-Univ 2.0: Monitoring the Digital and Social Environment of the University

  • Moreno, Isabel
  • Fernández Martínez, Javier
  • Gutiérrez, Yoan
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
Social-Univ 2.0 es una aplicación web que monitoriza el ecosistema digital de universidades con presencia en redes sociales y, más concretamente, se centra en analizar el entorno de la Universidad de Alicante. Usa las tecnologías del lenguaje humano para extraer meta-datos sobre comentarios en Twitter para representar perfiles de actores sociales, así como su relación social en un período de tiempo. Esta aplicación, en su primera versión: facilita tanto el estudio de interacciones sociales y sus matices, como el analisis de grupos sociales y sus comportamientos; identifica a actores sociales relevantes e influyentes, así como los temas comunes en determinados grupos sociales; y favorece la medición del impacto de campañas y eventos.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

Social Univ 2.0: Monitorización del entorno digital social universitario, Social Univ 2.0: Monitoring the Digital and Social Environment of the University

  • Gutiérrez, Yoan
  • Moreno, Isabel
  • Fernández Martínez, Javier
  • Martínez-Barco, Patricio
  • 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
Social-Univ 2.0 es una aplicación web que monitoriza el ecosistema digital de universidades con presencia en redes sociales. Su objetivo es, mediante tecnologías del lenguaje humano, analizar comentarios de la red social Twitter, así como los metadatos asociados, y relacionar actores mediante los mensajes en los que estos intervienen en un período de tiempo. Para iniciar el estudio social, el sistema requiere la definición de palabras claves que definan con precisión a la universidad que se desea observar en el entorno social. Estas palabras claves pueden ser identificadores (ej. @nickname), hashtags u otros elementos identificativos que señalen a una entidad digital en cuestión. A continuación, el sistema descarga comentarios de Twitter y los analiza semánticamente para valorar las diferentes posturas (ej. opiniones positivas, negativas y neutrales) que cada actor tiene respecto a otros, así como su influencia en el entorno digital-social. Por último, se muestra al usuario la información social analizada mediante grafos, perfiles y nubes de palabras en una interfaz que permite filtrar el análisis por periodos inferiores a 6 meses. Todo lo anterior permite a Social-Univ 2.0: (I) facilitar tanto el estudio de interacciones sociales y sus matices, como el análisis de grupos sociales y sus comportamientos; (II) identificar a actores sociales relevantes e influyentes, así como los temas comunes en determinados grupos sociales; y (III) y favorecer la medición del impacto de campañas y eventos. Una descripción más detallada del sistema completo se puede encontrar en [MFG19].
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

Dossier Next

  • Fernández Martínez, Javier
  • Gómez, José M.
  • Martínez-Barco, Patricio
  • Gutiérrez, Yoan
  • Llopis, Fernando
  • Muñoz, Rafael
  • Montoyo, Andres
  • Moreda, Paloma
  • Palomar, Manuel
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Llopis, Fernando|||/items/e8548380-b70f-44e7-a7fa-c7bed36990d8
  • Martínez-Barco, Patricio|||/items/f9630270-fe31-44c8-b611-dfaf9c109a4d
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Muñoz, Rafael|||/items/d6ef1286-fc50-4e8b-9d97-bcbc30e3d1bc
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
Dossier Next es una aplicación web que permite rastrear y clasificar de forma automática y periódica la información procedente de cualquier tipo de fuente de internet con contenido textual i.e. páginas web, periódicos digitales, boletines oficiales, etc., extrayendo únicamente la información más interesante para el usuario y descartando el resto. Para comenzar la recolección de información, el usuario debe indicar las fuentes a partir de las cuales desea obtener información, haciendo referencia a cada una las partes de interés para la recuperación de información, i.e. título, cuerpo, fecha, autor, etc. Para que el sistema pueda decidir qué contenido es relevante para el usuario, éste debe indicar también una serie de palabras claves, que deben aparecer en el documento en cuestión. Una vez establecida esta configuración del sistema se procede a descargar toda la información deseada por el usuario. Desde la página inicial se pueden visualizar los documentos por fecha y fuente.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

GPLSI FieroBoT: Asistente virtual para la captación de insultos, GPLSI FieroBoT: A virtual assistant for collecting insults

  • Botella-Gil, Beatriz
  • Gutiérrez, Yoan
  • Martínez-Barco, Patricio
  • Palomar, Manuel
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Martínez-Barco, Patricio|||/items/f9630270-fe31-44c8-b611-dfaf9c109a4d
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
  • Botella-Gil, Beatriz|||/items/a03c3d62-efa7-4c50-8870-103ca1d81d37
FieroBoT es un asistente virtual orientado a la recopilación de insultos desde la aplicación de mensajería Telegram. A través del sistema de mensajería de Telegram los usuarios pueden libremente tener una conversación con el robot donde se incita a que lo insultemos. El proceso es el siguiente, en primer lugar, se nos preguntará nuestro sexo y la edad y a continuación podremos insultar al robot. Solo se almacenará el contenido del mensaje y los datos demográficos genéricos como rango de edad y sexo con el fin de organizar el contenido. Los insultos recolectados servirán para la creación de un recurso de palabras y expresiones violentas que podrá ser utilizado para distintos estudios relacionados con el lenguaje popular.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Overview of the eHealth Knowledge Discovery Challenge at IberLEF 2021, Resumen de la Tarea de Descubrimiento de Conocimiento en Salud en IberLEF 2021

  • Piad-Morffis, Alejandro
  • Estévez-Velarde, Suilan
  • Gutiérrez, Yoan
  • Almeida-Cruz, Yudivian
  • Montoyo, Andres
  • Muñoz, Rafael
  • 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 summarises the eHealth Knowledge Discovery Challenge hosted at IberLEF 2021. We describe the task, resources, and participating systems, highlighting and discussing the main results achieved in the challenge. We analyse the best performing systems and present recommendations for future research.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Phonological Proximity in Costa Rican Sign Language

  • Naranjo-Zeledón, Luis
  • Chacón Rivas, Mario
  • Peral, Jesús
  • Ferrández, Antonio
  • Ferrández, Antonio|||/items/b77d3a3a-c05b-4aa1-921f-a0f269e50ba1
  • Peral, Jesús|||/items/c944ebfe-a23a-4bde-b779-e2054a62d1a7
The study of phonological proximity makes it possible to establish a basis for future decision-making in the treatment of sign languages. Knowing how close a set of signs are allows the interested party to decide more easily its study by clustering, as well as the teaching of the language to third parties based on similarities. In addition, it lays the foundation for strengthening disambiguation modules in automatic recognition systems. To the best of our knowledge, this is the first study of its kind for Costa Rican Sign Language (LESCO, for its Spanish acronym), and forms the basis for one of the modules of the already operational system of sign and speech editing called the International Platform for Sign Language Edition (PIELS). A database of 2665 signs, grouped into eight contexts, is used, and a comparison of similarity measures is made, using standard statistical formulas to measure their degree of correlation. This corpus will be especially useful in machine learning approaches. In this work, we have proposed an analysis of different similarity measures between signs in order to find out the phonological proximity between them. After analyzing the results obtained, we can conclude that LESCO is a sign language with high levels of phonological proximity, particularly in the orientation and location components, but they are noticeably lower in the form component. We have also concluded as an outstanding contribution of our research that automatic recognition systems can take as a basis for their first prototypes the contexts or sign domains that map to clusters with lower levels of similarity. As mentioned, the results obtained have multiple applications such as in the teaching area or the Natural Language Processing area for automatic recognition tasks.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Improving Open Data Web API Documentation through Interactivity and Natural Language Generation

  • González Mora, César
  • Barros, Cristina
  • Garrigós, Irene
  • Zubcoff, Jose
  • Lloret, Elena
  • Mazón, Jose-Norberto
  • Garrigós, Irene|||/items/50e21847-f541-4051-8e6d-4064e0e80ea3
  • González Mora, César|||/items/bffa7ade-023b-4e37-893a-cf0aa181e2d4
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Mazón, Jose-Norberto|||/items/31f8766d-f389-4889-ba06-adeb367a0753
  • Zubcoff, Jose|||/items/c8d086dc-e561-4ce4-9d9b-2db5c48a75f5
Widely adoption of Information Technologies has resulted in the continuous growing of open data available on the Web. However, the lack of suitable mechanisms to understand open data sources hampers its reusability. One way to overcome this limitation is by means of Web Application Programming Interfaces (APIs) with proper documentation, nowadays being the existing very rudimentary, hard to follow, and sometimes incomplete or even inaccurate in most cases. In order to improve the documentation of Web APIs that access open data, this paper proposes a novel approach to automatically generate interactive Web API documentation, both machine and user readable. This process starts by analysing the documentation of an API to obtain important information, automatically constructing Natural Language descriptions of the main Web API concepts by applying Natural Language Processing (NLP), and specifically, language generation techniques. Then, the documentation is made interactive by making it available as a Web interface, offering easy access to open data provided by Web APIs. Therefore, the use and comprehension of the Web APIs is facilitated, thus promoting the reusability of open data. The feasibility of our approach is presented through a case study and an experiment with users, both showing the benefits of our approach.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

HeadlineStanceChecker: Exploiting summarization to detect headline disinformation

  • 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
The headline of a news article is designed to succinctly summarize its content, providing the reader with a clear understanding of the news item. Unfortunately, in the post-truth era, headlines are more focused on attracting the reader’s attention for ideological or commercial reasons, thus leading to mis- or disinformation through false or distorted headlines. One way of combating this, although a challenging task, is by determining the relation between the headline and the body text to establish the stance. Hence, to contribute to the detection of mis- and disinformation, this paper proposes an approach—HeadlineStanceChecker—that determines the stance of a headline with respect to the body text to which it is associated. The novelty rests on the use of a two-stage classification architecture that uses summarization techniques to shape the input for both classifiers instead of directly passing the full news body text, thereby reducing the amount of information to be processed while keeping important information. Specifically, summarization is done through Positional Language Models leveraging on semantic resources to identify salient information in the body text that is then compared to its corresponding headline. The results obtained show that our approach achieves 94.31% accuracy for the overall classification and the best FNC-1 relative score compared with the state of the art. It is especially remarkable that the system, which uses only the relevant information provided by the automatic summaries instead of the whole text, is able to classify the different stance categories with very competitive results, especially in the discuss stance between the headline and the news body text. It can be concluded that using automatic extractive summaries as input of our approach together with the two-stage architecture is an appropriate solution to the problem.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

GPLSI AitanaWEB. Asistente Virtual sobre procesos de matriculación académica

  • Gutiérrez, Yoan
  • Abreu Salas, José Ignacio
  • Montoyo, Andres
  • Muñoz, Rafael
  • 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
AitanaWEB es un chatbot para la asistencia telemática a usuarios sobre los procesos de matriculación académica y cuestiones relacionadas. Ofrece información sobre temas como los Horarios, Notas de Corte, Matrícula, Traslado de Expediente entre otros. Esta diseñado orientado a la accesibilidad y la usabilidad, posibilitando el acceso en Valenciano y Castellano. Permite el acceso desde diferentes navegadores, como Chrome, Firefox, Edge, Chrome para Android y Safari. Incorpora un narrador y facilidades de reconocimiento del habla permitiendo al usuario realizar la interacción con el sistema mediante voz. El proyecto cuenta de dos componentes básicos: (i) uso de DialogFlow de Google como servicio de Inteligencia Artificial donde se estructuran y entrenan las preguntas y respuestas. (ii) componente de desarrollo propio que hace de controlador, intérprete y enrutador entre DialogFlow y la interfaz de usuario final.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

PCT Observer Tablero de Parques Científicos/Tecnológicos, PCT Observer

  • Francés, Olga
  • Abreu Salas, José Ignacio
  • Gutiérrez, Yoan
  • Fernández Martínez, Javier
  • 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
PCT Observer es una aplicación web para visualizar y analizar datos relacionados con los parques científicos/tecnológicos. Permite descubrir la existencia de diferencias significativas o relaciones entre los indicadores clave, comparar su evolución en el tiempo, y determinar los indicadores más relevantes para caracterizar los diferentes tipos de parques.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Architecture design of a reinforcement environment for learning sign languages

  • Naranjo-Zeledón, Luis
  • Chacón Rivas, Mario
  • Peral, Jesús
  • Ferrández, Antonio
  • Ferrández, Antonio|||/items/b77d3a3a-c05b-4aa1-921f-a0f269e50ba1
  • Peral, Jesús|||/items/c944ebfe-a23a-4bde-b779-e2054a62d1a7
Different fields such as linguistics, teaching, and computing have demonstrated special interest in the study of sign languages (SL). However, the processes of teaching and learning these languages turn complex since it is unusual to find people teaching these languages that are fluent in both SL and the native language of the students. The teachings from deaf individuals become unique. Nonetheless, it is important for the student to lean on supportive mechanisms while being in the process of learning an SL. Bidirectional communication between deaf and hearing people through SL is a hot topic to achieve a higher level of inclusion. However, all the processes that convey teaching and learning SL turn difficult and complex since it is unusual to find SL teachers that are fluent also in the native language of the students, making it harder to provide computer teaching tools for different SL. Moreover, the main aspects that a second language learner of an SL finds difficult are phonology, non-manual components, and the use of space (the latter two are specific to SL, not to spoken languages). This proposal appears to be the first of the kind to favor the Costa Rican Sign Language (LESCO, for its Spanish acronym), as well as any other SL. Our research focus stands on reinforcing the learning process of final-user hearing people through a modular architectural design of a learning environment, relying on the concept of phonological proximity within a graphical tool with a high degree of usability. The aim of incorporating phonological proximity is to assist individuals in learning signs with similar handshapes. This architecture separates the logic and processing aspects from those associated with the access and generation of data, which makes it portable to other SL in the future. The methodology used consisted of defining 26 phonological parameters (13 for each hand), thus characterizing each sign appropriately. Then, a similarity formula was applied to compare each pair of signs. With these pre-calculations, the tool displays each sign and its top ten most similar signs. A SUS usability test and an open qualitative question were applied, as well as a numerical evaluation to a group of learners, to validate the proposal. In order to reach our research aims, we have analyzed previous work on proposals for teaching tools meant for the student to practice SL, as well as previous work on the importance of phonological proximity in this teaching process. This previous work justifies the necessity of our proposal, whose benefits have been proved through the experimentation conducted by different users on the usability and usefulness of the tool. To meet these needs, homonymous words (signs with the same starting handshape) and paronyms (signs with highly similar handshape), have been included to explore their impact on learning. It allows the possibility to apply the same perspective of our existing line of research to other SL in the future.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Active Learning for Assisted Corpus Construction: A Case Study in Knowledge Discovery from Biomedical Text

  • Cañizares-Diaz, Hian
  • Piad-Morffis, Alejandro
  • Estévez-Velarde, Suilan
  • Gutiérrez, Yoan
  • Almeida-Cruz, Yudivian
  • Montoyo, Andres
  • Muñoz, Rafael
  • 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 an active learning approach that aims to reduce the human effort required during the annotation of natural language corpora composed of entities and semantic relations. Our approach assists human annotators by intelligently selecting the most informative sentences to annotate and then pre-annotating them with a few highly accurate entities and semantic relations. We define an uncertainty-based query strategy with a weighted density factor, using similarity metrics based on sentence embeddings. As a case study, we evaluate our approach via simulation in a biomedical corpus and estimate the potential reduction in total annotation time. Experimental results suggest that the query strategy reduces by between 35% and 40% the number of sentences that must be manually annotated to develop systems able to reach a target F1 score, while the pre-annotation strategy produces an additional 24% reduction in the total annotation time. Overall, our preliminary experiments suggest that as much as 60% of the annotation time could be saved while producing corpora that have the same usefulness for training machine learning algorithms. An open-source computational tool that implements the aforementioned strategies is presented and published online for the research community.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Communicative Intentions Annotation Scheme for Natural Language Generation

  • 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 text or message we want to express in our communicative interactions. With the purpose of contributing to the improvement of natural language generation systems, so that they can take the communicative intention as one of the starting points that will determine the structure and content of the message generated, the aim of this project is to create a communicative intentions annotation scheme based on the taxonomy presented in the Speech Act Theory. To do so, the scheme will be created with the help of a linguistic corpus and subsequently tested within a natural language generation system. In this way, it will be possible to check up to which point communicative intentions improve the planning stage of the text to be generated automatically, guiding the rest of decisions to be made by the system in order to create automatic messages with more similar results to any manually created text.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Optimizing Data-Driven Models for Summarization as Parallel Tasks

  • Zamuda, Aleš
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
This paper presents tackling of a hard optimization problem of computational linguistics, specifically automatic multi-document text summarization, using grid computing. The main challenge of multi-document summarization is to extract the most relevant and unique information effectively and efficiently from a set of topic-related documents, constrained to a specified length. In the Big Data/Text era, where the information increases exponentially, optimization becomes essential in selection of the most representative sentences for generating the best summaries. Therefore, a data-driven summarization model is proposed and optimized during a run of Differential Evolution (DE). Different DE runs are distributed to a grid in parallel as optimization tasks, seeking high processing throughput despite the demanding complexity of the linguistic model, especially on longer multi-documents where DE improves results given more iterations. Namely, parallelization and the grid enable, running several independent DE runs at same time within fixed real-time budget. Such approach results in improving a Document Understanding Conference (DUC) benchmark recall metric over a previous setting.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Leveraging Machine Learning to Explain the Nature of Written Genres

  • Vicente, Marta
  • Miró Maestre, María
  • 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
The analysis of discourse and the study of what characterizes it in terms of communicative objectives is essential to most tasks of Natural Language Processing. Consequently, research on textual genres as expressions of such objectives presents an opportunity to enhance both automatic techniques and resources. To conduct an investigation of this kind, it is necessary to have a good understanding of what defines and distinguishes each textual genre. This research presents a data-driven approach to discover and analyze patterns in several textual genres with the aim of identifying and quantifying the differences between them, considering how language is employed and meaning expressed in each particular case. To identify and analyze patterns within genres, a set of linguistic features is first defined, extracted and computed by using several Natural Language Processing tools. Specifically, the analysis is performed over a corpora of documents—containing news, tales and reviews—gathered from different sources to ensure an heterogeneous representation. Once the feature dataset has been generated, machine learning techniques are used to ascertain how and to what extent each of the features should be present in a document depending on its genre. The results show that the set of features defined is relevant for characterizing the different genres. Furthermore, the findings allow us to perform a qualitative analysis of such features, so that their usefulness and suitability is corroborated. The results of the research can benefit natural language discourse processing tasks, which are useful both for understanding and generating language.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Knowledge Discovery in COVID-19 Research Literature

  • Estevanell-Valladares, Ernesto L.
  • Piad-Morffis, Alejandro
  • Estévez-Velarde, Suilan
  • Gutiérrez, Yoan
  • Montoyo, Andres
  • Muñoz, Rafael
  • Almeida-Cruz, Yudivian
  • Estevanell-Valladares, Ernesto L.|||/items/d8b1af9a-112f-48de-813f-b4d8f1df8bd1
  • 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 the preliminary results of an ongoing project that analyzes the growing body of scientific research published around the COVID-19 pandemic. In this research, a general-purpose semantic model is used to double annotate a batch of 500 sentences that were manually selected from the CORD-19 corpus. Afterwards, a baseline text-mining pipeline is designed and evaluated via a large batch of 100,959 sentences. We present a qualitative analysis of the most interesting facts automatically extracted and highlight possible future lines of development. The preliminary results show that general-purpose semantic models are a useful tool for discovering fine-grained knowledge in large corpora of scientific documents.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Neural Natural Language Generation: A Survey on Multilinguality, Multimodality, Controllability and Learning

  • Erdem, Erkut
  • Kuyu, Menekse
  • Yagcioglu, Semih
  • Frank, Anette
  • Parcalabescu, Letitia
  • Babii, Andrii
  • Turuta, Oleksii
  • Erdem, Aykut
  • Calixto, Iacer
  • Lloret, Elena
  • Apostol, Elena-Simona
  • Truică, Ciprian-Octavian
  • Šandrih, Branislava
  • Martinčić-Ipšić, Sanda
  • Berend, Gábor
  • Gatt, Albert
  • Korvel, Grăzina
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
Developing artificial learning systems that can understand and generate natural language has been one of the long-standing goals of artificial intelligence. Recent decades have witnessed an impressive progress on both of these problems, giving rise to a new family of approaches. Especially, the advances in deep learning over the past couple of years have led to neural approaches to natural language generation (NLG). These methods combine generative language learning techniques with neural-networks based frameworks. With a wide range of applications in natural language processing, neural NLG (NNLG) is a new and fast growing field of research. In this state-of-the-art report, we investigate the recent developments and applications of NNLG in its full extent from a multidimensional view, covering critical perspectives such as multimodality, multilinguality, controllability and learning strategies. We summarize the fundamental building blocks of NNLG approaches from these aspects and provide detailed reviews of commonly used preprocessing steps and basic neural architectures. This report also focuses on the seminal applications of these NNLG models such as machine translation, description generation, automatic speech recognition, abstractive summarization, text simplification, question answering and generation, and dialogue generation. Finally, we conclude with a thorough discussion of the described frameworks by pointing out some open research directions.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

To what extent does content selection affect surface realization in the context of headline generation?

  • Barros, Cristina
  • Vicente, Marta
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
Headline generation is a task where the most important information of a news article is condensed and embodied into a single short sentence. This task is normally addressed by summarization techniques, ideally combining extractive and abstractive methods together with sentence compression or fusion techniques. Although Natural Language Generation (NLG) techniques have not been directly exploited for headline generation, they may provide better mechanisms than summarization techniques to paraphrase the information of a text. Therefore, this paper analyzes and evaluates the effectiveness of NLG techniques for generating headlines. In NLG, both content selection and surface realization are equally important—there is no point in generating text without knowing the topic. Considering this premise, we therefore take HanaNLG—a hybrid surface realization approach—as a basis, and we analyze the effect in the generated text when different content selection strategies are integrated at macroplanning stage. The experiments conducted show that, despite not using any sophisticated summarization method, the proposed approach provided the following benefits: i) it generated a coherent, linguistically structured headline; ii) it obtained results on standard datasets (i.e., DUC 2003 and DUC 2004) that were comparable to several competitive systems, in terms of the content of the generated headline; and, iii) the headlines generated by the whole approach (PLM-HanaNLG) were preferred by human assessors compared to those generated by the best performing system in DUC 2003.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Relevant Content Selection through Positional Language Models: An Exploratory Analysis, Selección de Contenido Relevante mediante Modelos de Lenguaje Posicionales: Un Análisis Experimental

  • Vicente, Marta
  • Lloret, Elena
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
Extractive Summarisation, like other areas in Natural Language Processing, has succumbed to the general trend marked by the success of neural approaches. However, the required resources-computational, temporal, data-are not always available. We present an experimental study of a method based on statistical techniques that, exploiting the semantic information from the source and its structure, provides competitive results against the state of the art. We propose a Discourse-Informed approach for Cost-effective Extractive Summarisation (DICES). DICES is an unsupervised, lightweight and adaptable framework that requires neither training data nor high-performance computing resources to achieve promising results.
RUA. Repositorio Institucional de la Universidad de Alicante
Software de investigación Software (Software)

Dossier Next Report

  • Fernández Martínez, Javier
  • Gutiérrez, Yoan
  • Martínez-Barco, Patricio
  • Gómez, José M.
  • Llopis, Fernando
  • Muñoz, Rafael
  • Montoyo, Andres
  • Moreda, Paloma
  • Palomar, Manuel
  • Fernández Martínez, Javier|||/items/f9b0416b-2411-47be-a586-11f90957e00f
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Llopis, Fernando|||/items/e8548380-b70f-44e7-a7fa-c7bed36990d8
  • Martínez-Barco, Patricio|||/items/f9630270-fe31-44c8-b611-dfaf9c109a4d
  • Montoyo, Andres|||/items/a2b7158a-7032-423a-a7b5-0f7b92902b72
  • Moreda, Paloma|||/items/aeb186ed-9034-4fdf-96fc-88941be830e7
  • Muñoz, Rafael|||/items/d6ef1286-fc50-4e8b-9d97-bcbc30e3d1bc
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
Dossier Next Report es una aplicación que permite generar resúmenes automáticos y análisis estadístico a partir de la base de datos de una aplicación Dossier Next. Simplemente se ha de indicar un intervalo de fechas y se generarán automáticamente varios resúmenes: uno general, teniendo en cuenta todos los documentos de ese período, y otro para cada entidad detectada dentro de los documentos de ese período. De esta forma, es posible obtener la información más importante de una colección de textos y de cada una de las entidades mencionadas en esa colección.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Intelligent Ensembling of Auto-ML System Outputs for Solving Classification Problems

  • 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
Automatic Machine Learning (Auto-ML) tools enable the automatic solution of real-world problems through machine learning techniques. These tools tend to be more time consuming than standard machine learning libraries, therefore, exploiting all the available resources to the full is a valuable feature. This paper presents a two-phase optimization system for solving classification problems. The system is designed to produce more robust classifiers by exploiting the different architectures that are generated while solving classification problems with Auto-ML tools, particularly AutoGOAL. In the first phase, the system follows a probabilistic strategy to find the best combination of algorithms and hyperparameters to generate a collection of base models according to certain diversity criteria; and in the second, it follows similar Auto-ML strategies to ensemble those models. The HAHA 2019 challenge corpus and the Adult dataset were used to evaluate the system. The experimental results show that: i) a better solution can be built by ensembling a subset of the already tested models; ii) the performance of ensemble methods depends on the collection of base models used; and, iii) ensuring diversity using the double-fault measure produces better results than the disagreement measure. The source code is available online for the research community.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Developing an ontology schema for enriching and linking digital media assets

  • Gutiérrez, Yoan
  • Tomás, David
  • Moreno, Isabel
  • Gutiérrez, Yoan|||/items/8f7f89db-a015-4ed6-85b9-75bd041ee8bd
  • Tomás, David|||/items/cf031fc3-3c30-454b-a6df-3762c29cc296
The abundance of digital media information coming from different sources, completely redefines approaches to media content production management and distribution for all contexts (i.e. technical, business and operational). Such content includes descriptive information (i.e. metadata) about an asset (e.g. a movie, song or game), as well as playable media (e.g. audio or video files). Metadata is organised following a variety of inconsistent structures and formats that are supplied by various content providers. Some challenges have been addressed in terms of standardising and enriching media assets metadata from a semantic perspective. Well known examples include Europeana and DBpedia. Nevertheless, due to the ongoing variability and evolution of digital contents, constant support and creation of new semantic representations are necessary. This article presents an ontology schema covering the requirements of users (content providers and content consumers) involved in the overall life cycle of a digital media asset, which has been designed and developed for a real scenario. The construction of this schema has been documented and evaluated following a methodology supported by quantitative and qualitative metrics. As part of the tangible results, the following outcomes were produced: (i) an RDF/XML schema available via Zenodo and GitHub; (ii) competence questions used for validation are published at GitHub; (iii) an exemplary ontology repository; and (iv) CRUD (Create, Read, Update and Delete) technologies for managing semantic repositories based on such schema. These results form an active part of the framework of a European project and other ongoing research initiatives.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

GPLSI team at CheckThat! 2021: Fine-tuning BETO and RoBERTa

  • Sepúlveda-Torres, Robiert
  • Saquete Boró, Estela
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
CheckThat! Lab is a challenging lab aimed at tackling the disinformation problem. The GPLSI team from the University of Alicante (Spain) has participated in two tasks of the CheckThat! Lab namely, Task 1 (Check-Worthiness Estimation) and Task 3 (Fake News Detection). We attained second and fifth place in the Spanish-version and English-version of Subtask 1A. Our systems use models based on transfer learning such as RoBERTa and BETO. The best results were achieved by fine-tuning these models. However, our results for Subtask 3A are low compared to the team that achieved the best result. We included some external features in the models for Subtask 1A and 3A, but we could not improve the results. In future work, we will experiment by incorporating other external features into the models with the aim of improving the results of the tasks.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Can Text Summarization Enhance the Headline Stance Detection Task? Benefits and Drawbacks

  • Vicente, Marta
  • Sepúlveda-Torres, Robiert
  • Barros, Cristina
  • Saquete-Boró, Estela
  • Lloret, Elena
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
This paper presents an exploratory study that analyzes the benefits and drawbacks of summarization techniques for the headline stance detection. Different types of summarization approaches are tested, as well as two stance detection methods (machine learning vs deep learning) on two state-of-the-art datasets (Emergent and FNC–1). Journalists’ headlines sourced from the Emergent dataset have demonstrated with very competitive results that they can be considered a summary of the news article. Based on this finding, this work evaluates the effectiveness of using summaries as a substitute for the full body text to determine the stance of a headline. As for automatic summarization methods, although there is still some room for improvement, several of the techniques analyzed show greater results compared to using the full body text—Lead Summarizer and PLM Summarizer are among the best-performing ones. In particular, PLM summarizer, especially when five sentences are selected as the summary length and deep learning is used, obtains the highest results compared to the other automatic summarization methods analyzed.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

A Systematic Mapping of Translation-Enabling Technologies for Sign Languages

  • Naranjo-Zeledón, Luis
  • Peral, Jesús
  • Ferrández, Antonio
  • Chacón Rivas, Mario
  • Ferrández, Antonio|||/items/b77d3a3a-c05b-4aa1-921f-a0f269e50ba1
  • Peral, Jesús|||/items/c944ebfe-a23a-4bde-b779-e2054a62d1a7
Sign languages (SL) are the first language for most deaf people. Consequently, bidirectional communication among deaf and non-deaf people has always been a challenging issue. Sign language usage has increased due to inclusion policies and general public agreement, which must then become evident in information technologies, in the many facets that comprise sign language understanding and its computational treatment. In this study, we conduct a thorough systematic mapping of translation-enabling technologies for sign languages. This mapping has considered the most recommended guidelines for systematic reviews, i.e., those pertaining software engineering, since there is a need to account for interdisciplinary areas of accessibility, human computer interaction, natural language processing, and education, all of them part of ACM (Association for Computing Machinery) computing classification system directly related to software engineering. An ongoing development of a software tool called SYMPLE (SYstematic Mapping and Parallel Loading Engine) facilitated the querying and construction of a base set of candidate studies. A great diversity of topics has been studied over the last 25 years or so, but this systematic mapping allows for comfortable visualization of predominant areas, venues, top authors, and different measures of concentration and dispersion. The systematic review clearly shows a large number of classifications and subclassifications interspersed over time. This is an area of study in which there is much interest, with a basically steady level of scientific publications over the last decade, concentrated mainly in the European continent. The publications by country, nevertheless, usually favor their local sign language.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Team GPLSI. Approach for automated fact checking

  • Alonso-Reina, Aimée
  • Sepúlveda-Torres, Robiert
  • Saquete Boró, Estela
  • Palomar, Manuel
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
Fever Shared 2.0 Task is a challenge meant for developing automated fact checking systems. Our approach for the Fever 2.0 is based on a previous proposal developed by Team Athene UKP TU Darmstadt. Our proposal modifies the sentence retrieval phase, using statement extraction and representation in the form of triplets (subject, object, action). Triplets are extracted from the claim and compare to triplets extracted from Wikipedia articles using semantic similarity. Our results are satisfactory but there is room for improvement.
RUA. Repositorio Institucional de la Universidad de Alicante
Publicación Otros (Other)

Exploring Summarization to Enhance Headline Stance Detection

  • Sepúlveda-Torres, Robiert
  • Vicente, Marta
  • Saquete Boró, Estela
  • Lloret, Elena
  • Palomar, Manuel
  • Sepúlveda-Torres, Robiert|||/items/60f24ee2-fe45-4b5c-a70c-c025ed1b5e4a
  • Saquete Boró, Estela|||/items/452393f2-fb8d-4840-b797-4b65a4bc9a87
  • Lloret, Elena|||/items/4593ef69-8308-49d3-8f0f-17e6ee078be5
  • Palomar, Manuel|||/items/71e8f2d8-8d56-4c8e-89df-d6ce2497d967
The spread of fake news and misinformation is causing serious problems to society, partly due to the fact that more and more people only read headlines or highlights of news assuming that everything is reliable, instead of carefully analysing whether it can contain distorted or false information. Specifically, the headline of a correctly designed news item must correspond to a summary of the main information of that news item. Unfortunately, this is not always happening, since various interests, such as increasing the number of clicks as well as political interests can be behind of the generation of a headlines that does not meet its intended original purpose. This paper analyses the use of automatic news summaries to determine the stance (i.e., position) of a headline with respect to the body of text associated with it. To this end, we propose a two-stage approach that uses summary techniques as input for both classifiers instead of the full text of the news body, thus reducing the amount of information that must be processed while maintaining the important information. The experimentation has been carried out using the Fake News Challenge FNC-1 dataset, leading to a 94.13% accuracy, surpassing the state of the art. It is especially remarkable that the proposed approach, which uses only the relevant information provided by the automatic summaries instead of the full text, is able to classify the different stance categories with very competitive results, so it can be concluded that the use of the automatic extractive summaries has a positive impact for determining the stance of very short information (i.e., headline, sentence) with respect to its whole content.