Semantic clustering of pivot paraphrases
International audience Paraphrases extracted from parallel corpora by the pivot method (Bannard and Callison-Burch, 2005) constitute a valuable resource for multilingual NLP applications. In this study, we analyse the semantics of unigram pivot paraphrases and use a graph-based sense induction appro...
Main Authors: | , , |
---|---|
Other Authors: | , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2014
|
Subjects: | |
Online Access: | https://hal.archives-ouvertes.fr/hal-01838559 |
id |
ftccsdartic:oai:HAL:hal-01838559v1 |
---|---|
record_format |
openpolar |
spelling |
ftccsdartic:oai:HAL:hal-01838559v1 2023-05-15T16:48:24+02:00 Semantic clustering of pivot paraphrases Apidianaki, Marianna Verzeni, Emilia McCarthy, Diana Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI) Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919) Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11) Reykjavik, Iceland 2014-01-01 https://hal.archives-ouvertes.fr/hal-01838559 en eng HAL CCSD hal-01838559 https://hal.archives-ouvertes.fr/hal-01838559 International Conference on Language Resources and Evaluation https://hal.archives-ouvertes.fr/hal-01838559 International Conference on Language Resources and Evaluation, Jan 2014, Reykjavik, Iceland parallel corpora sense clustering pivot paraphrasing [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] info:eu-repo/semantics/conferenceObject Conference papers 2014 ftccsdartic 2021-12-19T02:17:26Z International audience Paraphrases extracted from parallel corpora by the pivot method (Bannard and Callison-Burch, 2005) constitute a valuable resource for multilingual NLP applications. In this study, we analyse the semantics of unigram pivot paraphrases and use a graph-based sense induction approach to unveil hidden sense distinctions in the paraphrase sets. The comparison of the acquired senses to gold data from the Lexical Substitution shared task (McCarthy and Navigli, 2007) demonstrates that sense distinctions exist in the paraphrase sets and highlights the need for a disambiguation step in applications using this resource. Conference Object Iceland Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) Burch ENVELOPE(164.417,164.417,-70.817,-70.817) McCarthy ENVELOPE(66.543,66.543,-70.404,-70.404) Pivot ENVELOPE(-30.239,-30.239,-80.667,-80.667) |
institution |
Open Polar |
collection |
Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
op_collection_id |
ftccsdartic |
language |
English |
topic |
parallel corpora sense clustering pivot paraphrasing [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] |
spellingShingle |
parallel corpora sense clustering pivot paraphrasing [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] Apidianaki, Marianna Verzeni, Emilia McCarthy, Diana Semantic clustering of pivot paraphrases |
topic_facet |
parallel corpora sense clustering pivot paraphrasing [INFO]Computer Science [cs] [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] |
description |
International audience Paraphrases extracted from parallel corpora by the pivot method (Bannard and Callison-Burch, 2005) constitute a valuable resource for multilingual NLP applications. In this study, we analyse the semantics of unigram pivot paraphrases and use a graph-based sense induction approach to unveil hidden sense distinctions in the paraphrase sets. The comparison of the acquired senses to gold data from the Lexical Substitution shared task (McCarthy and Navigli, 2007) demonstrates that sense distinctions exist in the paraphrase sets and highlights the need for a disambiguation step in applications using this resource. |
author2 |
Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur (LIMSI) Université Paris Saclay (COmUE)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université - UFR d'Ingénierie (UFR 919) Sorbonne Université (SU)-Sorbonne Université (SU)-Université Paris-Saclay-Université Paris-Sud - Paris 11 (UP11) |
format |
Conference Object |
author |
Apidianaki, Marianna Verzeni, Emilia McCarthy, Diana |
author_facet |
Apidianaki, Marianna Verzeni, Emilia McCarthy, Diana |
author_sort |
Apidianaki, Marianna |
title |
Semantic clustering of pivot paraphrases |
title_short |
Semantic clustering of pivot paraphrases |
title_full |
Semantic clustering of pivot paraphrases |
title_fullStr |
Semantic clustering of pivot paraphrases |
title_full_unstemmed |
Semantic clustering of pivot paraphrases |
title_sort |
semantic clustering of pivot paraphrases |
publisher |
HAL CCSD |
publishDate |
2014 |
url |
https://hal.archives-ouvertes.fr/hal-01838559 |
op_coverage |
Reykjavik, Iceland |
long_lat |
ENVELOPE(164.417,164.417,-70.817,-70.817) ENVELOPE(66.543,66.543,-70.404,-70.404) ENVELOPE(-30.239,-30.239,-80.667,-80.667) |
geographic |
Burch McCarthy Pivot |
geographic_facet |
Burch McCarthy Pivot |
genre |
Iceland |
genre_facet |
Iceland |
op_source |
International Conference on Language Resources and Evaluation https://hal.archives-ouvertes.fr/hal-01838559 International Conference on Language Resources and Evaluation, Jan 2014, Reykjavik, Iceland |
op_relation |
hal-01838559 https://hal.archives-ouvertes.fr/hal-01838559 |
_version_ |
1766038497405173760 |