Skip to main content

SIMPLIFICACION DE TEXTOS MULTILINGUE Y DEPENDIENTE DEL CONTEXTO

PID2019-109066GB-I00

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos de I+D+i (Generación de Conocimiento y Retos Investigación)
Call year 2019
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POMPEU FABRA CCT

Resultados relacionados

Resultados totales (Incluyendo duplicados): 13
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Argumentation mining in scientific literature: from computational linguistics to biomedicine

  • Accuosto, Pablo
  • Neves, Mariana
  • Saggion, Horacio
Comunicació presentada al BIR 2021: 11th International Workshop on Bibliometric-enhanced Information Retrieval, celebrat l'1 d'abril de 2021 de manera virtual., In this work we propose to tackle the limitations posed by the lack of annotated data for argument mining in scientific texts by annotating argumentative units and relations in research abstracts in two scientific domains. We evaluate our annotations by computing inter-annotator agreements, which range from moderate to substantial according to the difficulty level of the tasks and domains. We use our newly annotated corpus to fine-tune BERT-based models for argument mining in single and multi-task settings, finally exploring the adaptation of models trained in one scientific discipline (computational linguistics) to predict the argumentative structure of abstracts in a different one (biomedicine)., This work was (partly) supported by the Spanish Government under the María de Maeztu Units of Excellence Programme (MDM-2015-0502) and by the Research and Innovation Agency of Uruguay (ANII). We also acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019-109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovación y Universidades (MCIU) and by Agencia Estatal de Investigación (AEI) of Spain.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

ALEXSIS: a dataset for lexical simplification in spanish

  • Ferrés, Daniel
  • Saggion, Horacio
Comunicació presentada a: LREC 2022, 13th International Conference on Language Resources and Evaluation, celebrat del 20 al 25 de juny de 2022 a Marsella, França, Lexical Simplification is the process of reducing the lexical complexity of a text by replacing difficult words with easier to read (or understand) expressions while preserving the original information and meaning. In this paper we introduce ALEXSIS, a new dataset for this task, and we use ALEXSIS to benchmark Lexical Simplification systems in Spanish. The paper describes the evaluation of three kind of approaches to Lexical Simplification: a thesaurus-based approach, a single transformers-based approach, and a combination of transformers. We also report state of the art results on a previous Lexical Simplification dataset for Spanish, We acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019- 109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovacion y Universidades (MCIU) ´ and by Agencia Estatal de Investigacion (AEI) of Spain.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Automatic detection of sexism in social media with a multilingual approach

  • Altin, Lutfiye Seda Mut
  • Saggion, Horacio
Comunicació presentada a: Iberian Languages Evaluation Forum (IberLEF 2021), celebrat el 21 de setembre de 2021 de manera virtual, This paper describes the participation of the LaSTUS/TALN team in the shared task EXIST: sEXism Identification in Social neTworks at IberLEF 2021. EXIST promotes the development of classification systems able to spot sexism in social media posts in English and Spanish. More specifically a binary classification task is proposed to classify posts in either sexist or not sexist, while a multi-class task challenges systems to identify the type of sexism present in the post. We address the two tasks with a transformers-based system applying a multi-lingual BERT model. The paper reports and discusses the results obtained by our team., Our work is partly supported from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019-109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovaci´on y Universidades (MCIU) and by Agencia Estatal de Investigaci´on (AEI) of Spain.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Preface to the First Workshop on current trends in text simplification

Repositorio Digital de la UPF
Publication Artículo científico (JournalArticle)

Lexical simplification benchmarks for English, Portuguese, and Spanish

  • Štajner, Sanja
  • Ferrés, Daniel
  • Shardlow, Matthew
  • North, Kai
  • Zampieri, Marcos
  • Saggion, Horacio
Even in highly-developed countries, as many as 15–30% of the population can only understand texts written using a basic vocabulary. Their understanding of everyday texts is limited, which prevents them from taking an active role in society and making informed decisions regarding healthcare, legal representation, or democratic choice. Lexical simplification is a natural language processing task that aims to make text understandable to everyone by replacing complex vocabulary and expressions with simpler ones, while preserving the original meaning. It has attracted considerable attention in the last 20 years, and fully automatic lexical simplification systems have been proposed for various languages. The main obstacle for the progress of the field is the absence of high-quality datasets for building and evaluating lexical simplification systems. In this study, we present a new benchmark dataset for lexical simplification in English, Spanish, and (Brazilian) Portuguese, and provide details about data selection and annotation procedures, to enable compilation of comparable datasets in other languages and domains. As the first multilingual lexical simplification dataset, where instances in all three languages were selected and annotated using comparable procedures, this is the first dataset that offers a direct comparison of lexical simplification systems for three languages. To showcase the usability of the dataset, we adapt two state-of-the-art lexical simplification systems with differing architectures (neural vs. non-neural) to all three languages (English, Spanish, and Brazilian Portuguese) and evaluate their performances on our new dataset. For a fairer comparison, we use several evaluation measures which capture varied aspects of the systems' efficacy, and discuss their strengths and weaknesses. We find that a state-of-the-art neural lexical simplification system outperforms a state-of-the-art non-neural lexical simplification system in all three languages, according to all evaluation measures. More importantly, we find that the state-of-the-art neural lexical simplification systems perform significantly better for English than for Spanish and Portuguese, thus posing a question if such an architecture can be used for successful lexical simplification in other languages, especially the low-resourced ones., HS and DF acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019-109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovación y Universidades (MCIU) and by Agencia Estatal de Investigación (AEI) of Spain.
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

A select and rewrite approach to the generation of related work reports

  • AbuRa'ed, Ahmed Ghassan Tawfiq
  • Saggion, Horacio
Comunicació presentada al BIR 2021: 11th International Workshop on Bibliometric-enhanced Information Retrieval, celebrat l'1 d'abril de 2021 de manera virtual., A related work report is a text which integrates key information from a list of related scientific papers providing context to the work being presented. In this paper we study the automatic generation of related work reports using extractive and abstractive text summarization approaches. Our extractive approach scores the sentences of the scientific papers based on their citations, selecting top scored sentences from each scientific paper to be mentioned in the related work report. The sentences are then organized in the report according to the topic they belong to. In additional experiments we use top scored sentences from our extractive methods and rephrase them using pre-trained abstractive models that generate citation sentences. We discuss automatic and manual evaluation of the generated related work reports showing the viability of the proposed approaches., This work was (partly) supported by the Spanish Government under the María de Maeztu Units of Excellence Programme (MDM-2015-0502). We also acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019- 109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovación y Universidades (MCIU) and by Agencia Estatal de Investigación (AEI) of Spain.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

A select and rewrite approach to the generation of related work reports

  • AbuRa'ed, Ahmed Ghassan Tawfiq
  • Saggion, Horacio
Comunicació presentada al BIR 2021: 11th International Workshop on Bibliometric-enhanced Information Retrieval, celebrat l'1 d'abril de 2021 de manera virtual., A related work report is a text which integrates key information from a list of related scientific papers providing context to the work being presented. In this paper we study the automatic generation of related work reports using extractive and abstractive text summarization approaches. Our extractive approach scores the sentences of the scientific papers based on their citations, selecting top scored sentences from each scientific paper to be mentioned in the related work report. The sentences are then organized in the report according to the topic they belong to. In additional experiments we use top scored sentences from our extractive methods and rephrase them using pre-trained abstractive models that generate citation sentences. We discuss automatic and manual evaluation of the generated related work reports showing the viability of the proposed approaches., This work was (partly) supported by the Spanish Government under the María de Maeztu Units of Excellence Programme (MDM-2015-0502). We also acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019- 109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovación y Universidades (MCIU) and by Agencia Estatal de Investigación (AEI) of Spain.
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Lexical simplification benchmarks for English, Portuguese, and Spanish

  • Štajner, Sanja
  • Ferrés, Daniel
  • Shardlow, Matthew
  • North, Kai
  • Zampieri, Marcos
  • Saggion, Horacio
Even in highly-developed countries, as many as 15–30% of the population can only understand texts written using a basic vocabulary. Their understanding of everyday texts is limited, which prevents them from taking an active role in society and making informed decisions regarding healthcare, legal representation, or democratic choice. Lexical simplification is a natural language processing task that aims to make text understandable to everyone by replacing complex vocabulary and expressions with simpler ones, while preserving the original meaning. It has attracted considerable attention in the last 20 years, and fully automatic lexical simplification systems have been proposed for various languages. The main obstacle for the progress of the field is the absence of high-quality datasets for building and evaluating lexical simplification systems. In this study, we present a new benchmark dataset for lexical simplification in English, Spanish, and (Brazilian) Portuguese, and provide details about data selection and annotation procedures, to enable compilation of comparable datasets in other languages and domains. As the first multilingual lexical simplification dataset, where instances in all three languages were selected and annotated using comparable procedures, this is the first dataset that offers a direct comparison of lexical simplification systems for three languages. To showcase the usability of the dataset, we adapt two state-of-the-art lexical simplification systems with differing architectures (neural vs. non-neural) to all three languages (English, Spanish, and Brazilian Portuguese) and evaluate their performances on our new dataset. For a fairer comparison, we use several evaluation measures which capture varied aspects of the systems' efficacy, and discuss their strengths and weaknesses. We find that a state-of-the-art neural lexical simplification system outperforms a state-of-the-art non-neural lexical simplification system in all three languages, according to all evaluation measures. More importantly, we find that the state-of-the-art neural lexical simplification systems perform significantly better for English than for Spanish and Portuguese, thus posing a question if such an architecture can be used for successful lexical simplification in other languages, especially the low-resourced ones., HS and DF acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019-109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovación y Universidades (MCIU) and by Agencia Estatal de Investigación (AEI) of Spain.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Preface to the First Workshop on current trends in text simplification

Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

ALEXSIS: a dataset for lexical simplification in spanish

  • Ferrés, Daniel
  • Saggion, Horacio
Comunicació presentada a: LREC 2022, 13th International Conference on Language Resources and Evaluation, celebrat del 20 al 25 de juny de 2022 a Marsella, França, Lexical Simplification is the process of reducing the lexical complexity of a text by replacing difficult words with easier to read (or understand) expressions while preserving the original information and meaning. In this paper we introduce ALEXSIS, a new dataset for this task, and we use ALEXSIS to benchmark Lexical Simplification systems in Spanish. The paper describes the evaluation of three kind of approaches to Lexical Simplification: a thesaurus-based approach, a single transformers-based approach, and a combination of transformers. We also report state of the art results on a previous Lexical Simplification dataset for Spanish, We acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019- 109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovacion y Universidades (MCIU) ´ and by Agencia Estatal de Investigacion (AEI) of Spain.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Automatic detection of sexism in social media with a multilingual approach

  • Altin, Lutfiye Seda Mut
  • Saggion, Horacio
Comunicació presentada a: Iberian Languages Evaluation Forum (IberLEF 2021), celebrat el 21 de setembre de 2021 de manera virtual, This paper describes the participation of the LaSTUS/TALN team in the shared task EXIST: sEXism Identification in Social neTworks at IberLEF 2021. EXIST promotes the development of classification systems able to spot sexism in social media posts in English and Spanish. More specifically a binary classification task is proposed to classify posts in either sexist or not sexist, while a multi-class task challenges systems to identify the type of sexism present in the post. We address the two tasks with a transformers-based system applying a multi-lingual BERT model. The paper reports and discusses the results obtained by our team., Our work is partly supported from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019-109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovaci´on y Universidades (MCIU) and by Agencia Estatal de Investigaci´on (AEI) of Spain.
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Argumentation mining in scientific literature: from computational linguistics to biomedicine

  • Accuosto, Pablo
  • Neves, Mariana
  • Saggion, Horacio
Comunicació presentada al BIR 2021: 11th International Workshop on Bibliometric-enhanced Information Retrieval, celebrat l'1 d'abril de 2021 de manera virtual., In this work we propose to tackle the limitations posed by the lack of annotated data for argument mining in scientific texts by annotating argumentative units and relations in research abstracts in two scientific domains. We evaluate our annotations by computing inter-annotator agreements, which range from moderate to substantial according to the difficulty level of the tasks and domains. We use our newly annotated corpus to fine-tune BERT-based models for argument mining in single and multi-task settings, finally exploring the adaptation of models trained in one scientific discipline (computational linguistics) to predict the argumentative structure of abstracts in a different one (biomedicine)., This work was (partly) supported by the Spanish Government under the María de Maeztu Units of Excellence Programme (MDM-2015-0502) and by the Research and Innovation Agency of Uruguay (ANII). We also acknowledge support from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019-109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovación y Universidades (MCIU) and by Agencia Estatal de Investigación (AEI) of Spain.
RUA. Repositorio Institucional de la Universidad de Alicante
Publication Otros (Other)

Multilingual Controllable Transformer-Based Lexical Simplification, Simplificación Léxica Controlable Multilingüe con Transformers

  • Sheang, Kim Cheng
  • Saggion, Horacio
Text is by far the most ubiquitous source of knowledge and information and should be made easily accessible to as many people as possible; however, texts often contain complex words that hinder reading comprehension and accessibility. Therefore, suggesting simpler alternatives for complex words without compromising meaning would help convey the information to a broader audience. This paper proposes mTLS, a multilingual controllable Transformer-based Lexical Simplification (LS) system fined-tuned with the T5 model. The novelty of this work lies in the use of language-specific prefixes, control tokens, and candidates extracted from pretrained masked language models to learn simpler alternatives for complex words. The evaluation results on three well-known LS datasets – LexMTurk, BenchLS, and NNSEval – show that our model outperforms the previous state-of-the-art models like LSBert and ConLS. Moreover, further evaluation of our approach on the part of the recent TSAR-2022 multilingual LS shared-task dataset shows that our model performs competitively when compared with the participating systems for English LS and even outperforms the GPT-3 model on several metrics. Moreover, our model obtains performance gains also for Spanish and Portuguese.