Pasar al contenido principal

SCENARIO KNOWLEDGE ACQUISITION BY TEXT READING: TERMINOLOGY KNOWLEDGE (SKATER-UPF-IULA)

TIN2012-38584-C06-05

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Nacional de Proyectos de Investigación Fundamental
Subprograma Subprograma de Proyectos de Investigación Fundamental no Orientada
Convocatoria Proyectos I+D
Año convocatoria 2012
Plan Estatal 2008-2011 Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica
Unidad de gestión Secretaría de Estado de Investigación, Desarrollo e Innovación
Centro beneficiario UNIVERSITAT POMPEU FABRA CCT
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

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

Towards the automatic classification of complex-type nominals

  • Romeo, Lauren
  • Mendes, Sara
  • Bel Rafecas, Núria
Comunicació presentada a: 6th International Conference on Generative Approaches to the Lexicon, celebrada a Pisa, Itàlia, del 24 al 25 de setembre del 2013., The work presented here depicts experiments toward the automatic classification of complex-type nominals using distributional information. We conducted two experiments: classifying complex-type nominals as members of multiple individual lexical classes, and building a dedicated classifier for complex-type nominals, distinguishing them from simple types. We discuss the promising results obtained, with a focus on asymmetries observed and on lines to be explored in the future., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by SKATER TIN2012-38584-C06-05 and by Fundação para a Ciência e a Tecnologia (FCT) post-doctoral fellowship SFRH/BPD/79900/2011.
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Class-based word sense induction for dot-type nominals

  • Romeo, Lauren
  • Martínez Alonso, Héctor
  • Bel Rafecas, Núria
Comunicació presentada a: 6th International Conference on Generative Approaches to the Lexicon, celebrada a Pisa, Itàlia, del 24 al 25 de setembre del 2013., This paper describes an effort to capture the sense alternation of dot-type nominals using Word Sense Induction (WSI). We propose dot-type nominals generate more semantically consistent groupings when clustered into more than two clusters, accounting for literal, metonymic and underspecified senses. Using a class-based approach, we replace individual lemmas with a placeholder representing the entire dot type, which also compensates for data sparsity. Although the distributional evidence does not motivate an individual cluster for each sense, we discuss how our results empirically support theoretical proposals regarding dot types., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by the European Commission’s 7th Framework Program under grant agreement 238405 (CLARA) and by SKATER TIN2012-38584-C06-05.
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Reading between the lines: overcoming data sparsity for accurate classification of lexical relationships

  • Necşulescu, Silvia
  • Mendes, Sara
  • Jurgens, David
  • Bel Rafecas, Núria
  • Navigli, Roberto
Comunicació presentada a: 4th Joint Conference on Lexical and Computational Semantics, celebrada a Denver, Colorado, Estats Units d'Amèrica, del 4 al 5 de juny de 2015., The lexical semantic relationships between word pairs are key features for many NLP tasks. Most approaches for automatically classifying related word pairs are hindered by data sparsity because of their need to observe two words co-occurring in order to detect the lexical relation holding between them. Even when mining very large corpora, not every related word pair co-occurs. Using novel representations based on graphs and word embeddings, we present two systems that are able to predict relations between words, even when these are never found in the same sentence in a given corpus. In two experiments, we demonstrate superior performance of both approaches over the state of the art, achieving significant gains in recall., The authors gratefully acknowledge the support of the CLARA project (EU-7FP-ITN-238405), the SKATER project (Ministerio de Economia y Competitividad, TIN2012-38584-C06-05) and of the MultiJEDI ERC Starting Grant no. 259234.
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

A cascade approach for complex-type classification

  • Romeo, Lauren
  • Mendes, Sara
  • Bel Rafecas, Núria
Comunicació presentada a: Ninth International Conference on Language Resources and Evaluation, celebrada a Reykjavik, Iceland, del 26 al 31 de maig de 2014., The work detailed in this paper describes a 2-step cascade approach for the classification of complex-type nominals. We describe an experiment that demonstrates how a cascade approach performs when the task consists in distinguishing nominals from a given complex-type from any other noun in the language. Overall, our classifier successfully identifies very specific and not highly frequent lexical items such as complex-types with high accuracy, and distinguishes them from those instances that are not complex types by using lexico-syntactic patterns indicative of the semantic classes corresponding to each of the individual sense components of the complex type. Although there is still room for improvement with regard to the coverage of the classifiers developed, the cascade approach increases the precision of classification of the complex-type nouns that are covered in the experiment presented., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by SKATER TIN2012-38584-C06-05, and by Fundação para a Ciência e a Tecnologia (FCT) post-doctoral fellowship SFRH/BPD/79900/2011.
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Boosting the creation of a treebank

  • Arias Badia, Blanca
  • Bel Rafecas, Núria
  • Fomicheva, Marina
  • Larrea Mendizabal, Imanol
  • Lorente, Mercè
  • Marimon, Montserrat
  • Milà-Garcia, Alba
  • Vivaldi, J. (Jorge), 1952-
  • Padró, Muntsa
Comunicació presentada al 9th International Conference on Language Resources and Evaluation (LREC'14), celebrat del 26 al 31 de maig de 2014 a Reykjavík, Islàndia., We present the results of the experiment of bootstrapping a Treebank for Catalan by using a Dependency Parser trained with Spanish sentences. In order to save time and cost, our approach was to profit from the typological similarities between Catalan and Spanish to create a first Catalan data set quickly by (i) automatically annotating with a delexicalized Spanish parser, (ii) manually correcting the parses, and (iii) using the Catalan corrected sentences to train a Catalan parser. The results showed that the number of parsed sentences required to train a Catalan parser is about 1000, which were achieved in 4 months with 2 annotators., This work was partially supported by the SKATER project (Ministerio de Economía y Competitividad, TIN2012-38584-C06-05).
Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

Choosing which to use? A study of distributional models for nominal lexical semantic classification

  • Romeo, Lauren
  • Lebani, Gianluca E.
  • Bel Rafecas, Núria
  • Lenci, Alessandro
Comunicació presentada a: Ninth International Conference on Language Resources and Evaluation, celebrada a Reykjavik, Iceland, del 26 al 31 de maig de 2014., This paper empirically evaluates the performances of different state-of-the-art distributional models in a nominal lexical semantic classification task. We consider models that exploit various types of distributional features, which thereby provide different representations of nominal behavior in context. The experiments presented in this work demonstrate the advantages and disadvantages of each model considered. This analysis also considers a combined strategy that we found to be capable of leveraging the bottlenecks of each model, especially when large robust data is not available., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by SKATER TIN2012-38584-C06-05 and the EBES-IULA/UPF mobility grant, as well as the PRIN grant 20105B3HE8 ”Word Combinations in Italian: theoretical and descriptive analysis, computational models, lexicographic layout and creation of a dictionary”, funded by the Italian Ministry of Education, University and Research.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Reading between the lines: overcoming data sparsity for accurate classification of lexical relationships

  • Necşulescu, Silvia
  • Mendes, Sara
  • Jurgens, David
  • Bel Rafecas, Núria
  • Navigli, Roberto
Comunicació presentada a: 4th Joint Conference on Lexical and Computational Semantics, celebrada a Denver, Colorado, Estats Units d'Amèrica, del 4 al 5 de juny de 2015., The lexical semantic relationships between word pairs are key features for many NLP tasks. Most approaches for automatically classifying related word pairs are hindered by data sparsity because of their need to observe two words co-occurring in order to detect the lexical relation holding between them. Even when mining very large corpora, not every related word pair co-occurs. Using novel representations based on graphs and word embeddings, we present two systems that are able to predict relations between words, even when these are never found in the same sentence in a given corpus. In two experiments, we demonstrate superior performance of both approaches over the state of the art, achieving significant gains in recall., The authors gratefully acknowledge the support of the CLARA project (EU-7FP-ITN-238405), the SKATER project (Ministerio de Economia y Competitividad, TIN2012-38584-C06-05) and of the MultiJEDI ERC Starting Grant no. 259234.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Choosing which to use? A study of distributional models for nominal lexical semantic classification

  • Romeo, Lauren
  • Lebani, Gianluca E.
  • Bel Rafecas, Núria
  • Lenci, Alessandro
Comunicació presentada a: Ninth International Conference on Language Resources and Evaluation, celebrada a Reykjavik, Iceland, del 26 al 31 de maig de 2014., This paper empirically evaluates the performances of different state-of-the-art distributional models in a nominal lexical semantic classification task. We consider models that exploit various types of distributional features, which thereby provide different representations of nominal behavior in context. The experiments presented in this work demonstrate the advantages and disadvantages of each model considered. This analysis also considers a combined strategy that we found to be capable of leveraging the bottlenecks of each model, especially when large robust data is not available., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by SKATER TIN2012-38584-C06-05 and the EBES-IULA/UPF mobility grant, as well as the PRIN grant 20105B3HE8 ”Word Combinations in Italian: theoretical and descriptive analysis, computational models, lexicographic layout and creation of a dictionary”, funded by the Italian Ministry of Education, University and Research.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Class-based word sense induction for dot-type nominals

  • Romeo, Lauren
  • Martínez Alonso, Héctor
  • Bel Rafecas, Núria
Comunicació presentada a: 6th International Conference on Generative Approaches to the Lexicon, celebrada a Pisa, Itàlia, del 24 al 25 de setembre del 2013., This paper describes an effort to capture the sense alternation of dot-type nominals using Word Sense Induction (WSI). We propose dot-type nominals generate more semantically consistent groupings when clustered into more than two clusters, accounting for literal, metonymic and underspecified senses. Using a class-based approach, we replace individual lemmas with a placeholder representing the entire dot type, which also compensates for data sparsity. Although the distributional evidence does not motivate an individual cluster for each sense, we discuss how our results empirically support theoretical proposals regarding dot types., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by the European Commission’s 7th Framework Program under grant agreement 238405 (CLARA) and by SKATER TIN2012-38584-C06-05.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Boosting the creation of a treebank

  • Arias Badia, Blanca
  • Bel Rafecas, Núria
  • Fomicheva, Marina
  • Larrea Mendizabal, Imanol
  • Lorente, Mercè
  • Marimon, Montserrat
  • Milà-Garcia, Alba
  • Vivaldi, J. (Jorge), 1952-
  • Padró, Muntsa
Comunicació presentada al 9th International Conference on Language Resources and Evaluation (LREC'14), celebrat del 26 al 31 de maig de 2014 a Reykjavík, Islàndia., We present the results of the experiment of bootstrapping a Treebank for Catalan by using a Dependency Parser trained with Spanish sentences. In order to save time and cost, our approach was to profit from the typological similarities between Catalan and Spanish to create a first Catalan data set quickly by (i) automatically annotating with a delexicalized Spanish parser, (ii) manually correcting the parses, and (iii) using the Catalan corrected sentences to train a Catalan parser. The results showed that the number of parsed sentences required to train a Catalan parser is about 1000, which were achieved in 4 months with 2 annotators., This work was partially supported by the SKATER project (Ministerio de Economía y Competitividad, TIN2012-38584-C06-05).
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

A cascade approach for complex-type classification

  • Romeo, Lauren
  • Mendes, Sara
  • Bel Rafecas, Núria
Comunicació presentada a: Ninth International Conference on Language Resources and Evaluation, celebrada a Reykjavik, Iceland, del 26 al 31 de maig de 2014., The work detailed in this paper describes a 2-step cascade approach for the classification of complex-type nominals. We describe an experiment that demonstrates how a cascade approach performs when the task consists in distinguishing nominals from a given complex-type from any other noun in the language. Overall, our classifier successfully identifies very specific and not highly frequent lexical items such as complex-types with high accuracy, and distinguishes them from those instances that are not complex types by using lexico-syntactic patterns indicative of the semantic classes corresponding to each of the individual sense components of the complex type. Although there is still room for improvement with regard to the coverage of the classifiers developed, the cascade approach increases the precision of classification of the complex-type nouns that are covered in the experiment presented., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by SKATER TIN2012-38584-C06-05, and by Fundação para a Ciência e a Tecnologia (FCT) post-doctoral fellowship SFRH/BPD/79900/2011.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Towards the automatic classification of complex-type nominals

  • Romeo, Lauren
  • Mendes, Sara
  • Bel Rafecas, Núria
Comunicació presentada a: 6th International Conference on Generative Approaches to the Lexicon, celebrada a Pisa, Itàlia, del 24 al 25 de setembre del 2013., The work presented here depicts experiments toward the automatic classification of complex-type nominals using distributional information. We conducted two experiments: classifying complex-type nominals as members of multiple individual lexical classes, and building a dedicated classifier for complex-type nominals, distinguishing them from simple types. We discuss the promising results obtained, with a focus on asymmetries observed and on lines to be explored in the future., This work was funded with the support of the SUR of the DEC of the Generalitat de Catalunya and the European Social Fund, by SKATER TIN2012-38584-C06-05 and by Fundação para a Ciência e a Tecnologia (FCT) post-doctoral fellowship SFRH/BPD/79900/2011.