Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 10
Encontrada(s) 1 página(s)

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

Finding dependency parsing limits over a large Spanish Corpus

  • Padró, Muntsa
  • Ballesteros, Miguel
  • Martínez, Héctor
  • Bohnet, Bernd
This paper studies the performance of different parsers over a large Spanish treebank. The aim of this work is to assess the limitations of state-of-the-art parsers. We want to select the most appropriate parser for subcategorization Frame acquisition, and we focus our analysis on two aspects: the accuracy drop when parsing out-of-domain data, and the performance over specific labels relevant to our task., HM has been partially funded by the European Commission’s 7th Framework Program under grant agreement 238405 (CLARA). MP has been funded by the European Project PANACEA (FP7-ICT-2010- 248064).
Repositorio Digital de la UPF
Publication 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
Publication Contribución de congreso (ConferenceOutput)

Annotation of regular polysemy and underspecification

  • Martínez Alonso, Héctor
  • Sandford Pedersen, Bolette
  • Bel Rafecas, Núria
Comunicació presentada a: 51st Annual Meeting of the Association for Computational Linguistics, celebrat a Sofia, Bulgaria, del 4 al 9 d'agost de 2013., We present the result of an annotation task on regular polysemy for a series of semantic classes or dot types in English, Danish and Spanish. This article describes the annotation process, the results in terms of inter-encoder agreement, and the sense distributions obtained with two methods: majority voting with a theory-compliant backoff strategy, and MACE, an unsupervised system to choose the most likely sense from all the annotations., The research leading to these results has been funded by the European Commission’s 7th Framework Program under grant agreement 238405 (CLARA).
Repositorio Digital de la UPF
Publication Contribución de congreso (ConferenceOutput)

Identification of sense selection in regular polysemy using shallow features

  • Martínez Alonso, Héctor
  • Sandford Pedersen, Bolette
  • Bel Rafecas, Núria
Comunicació presentada a: 18th Nordic Conference of Computational Linguistics NODALIDA 2011, celebrada a Riga, Latvia, del 11 al 13 de maig de 2011., The following work describes a method to automatically classify the sense selection of the complex type Location/Organization –which depends on regular polysemy– using shallow features, as well as a way to increase the volume of sense-selection gold standards by using monosemous data as filler. The classifier results show that grammatical features are the most relevant cues for the identification of sense selection in this instance of regular polysemy., The research leading to these results has received funding from the European Commission’s 7th Framework Program under grant agreement n°238405 (CLARA).
Repositorio Digital de la UPF
Publication 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
Publication Contribución de congreso (ConferenceOutput)

Finding dependency parsing limits over a large Spanish Corpus

  • Padró, Muntsa
  • Ballesteros, Miguel
  • Martínez, Héctor
  • Bohnet, Bernd
This paper studies the performance of different parsers over a large Spanish treebank. The aim of this work is to assess the limitations of state-of-the-art parsers. We want to select the most appropriate parser for subcategorization Frame acquisition, and we focus our analysis on two aspects: the accuracy drop when parsing out-of-domain data, and the performance over specific labels relevant to our task., HM has been partially funded by the European Commission’s 7th Framework Program under grant agreement 238405 (CLARA). MP has been funded by the European Project PANACEA (FP7-ICT-2010- 248064).
Recercat. Dipósit de la Recerca de Catalunya
Publication 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
Publication Contribución de congreso (ConferenceOutput)

Annotation of regular polysemy and underspecification

  • Martínez Alonso, Héctor
  • Sandford Pedersen, Bolette
  • Bel Rafecas, Núria
Comunicació presentada a: 51st Annual Meeting of the Association for Computational Linguistics, celebrat a Sofia, Bulgaria, del 4 al 9 d'agost de 2013., We present the result of an annotation task on regular polysemy for a series of semantic classes or dot types in English, Danish and Spanish. This article describes the annotation process, the results in terms of inter-encoder agreement, and the sense distributions obtained with two methods: majority voting with a theory-compliant backoff strategy, and MACE, an unsupervised system to choose the most likely sense from all the annotations., The research leading to these results has been funded by the European Commission’s 7th Framework Program under grant agreement 238405 (CLARA).
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Identification of sense selection in regular polysemy using shallow features

  • Martínez Alonso, Héctor
  • Sandford Pedersen, Bolette
  • Bel Rafecas, Núria
Comunicació presentada a: 18th Nordic Conference of Computational Linguistics NODALIDA 2011, celebrada a Riga, Latvia, del 11 al 13 de maig de 2011., The following work describes a method to automatically classify the sense selection of the complex type Location/Organization –which depends on regular polysemy– using shallow features, as well as a way to increase the volume of sense-selection gold standards by using monosemous data as filler. The classifier results show that grammatical features are the most relevant cues for the identification of sense selection in this instance of regular polysemy., The research leading to these results has received funding from the European Commission’s 7th Framework Program under grant agreement n°238405 (CLARA).
Recercat. Dipósit de la Recerca de Catalunya
Publication 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.