Semantic frame induction through the detection of communities of verbs and their arguments
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10071/21299 |
Resumo: | Resources such as FrameNet, which provide sets of semantic frame definitions and annotated textual data that maps into the evoked frames, are important for several NLP tasks. However, they are expensive to build and, consequently, are unavailable for many languages and domains. Thus, approaches able to induce semantic frames in an unsupervised manner are highly valuable. In this paper we approach that task from a network perspective as a community detection problem that targets the identification of groups of verb instances that evoke the same semantic frame and verb arguments that play the same semantic role. To do so, we apply a graph-clustering algorithm to a graph with contextualized representations of verb instances or arguments as nodes connected by edges if the distance between them is below a threshold that defines the granularity of the induced frames. By applying this approach to the benchmark dataset defined in the context of SemEval 2019, we outperformed all of the previous approaches to the task, achieving the current state-of-the-art performance. |
id |
RCAP_b9e424670ac6f4b24fc09c32979804b8 |
---|---|
oai_identifier_str |
oai:repositorio.iscte-iul.pt:10071/21299 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Semantic frame induction through the detection of communities of verbs and their argumentsSemantic framesSemantic rolesContextualized representationsCommunity detectionGraph clusteringResources such as FrameNet, which provide sets of semantic frame definitions and annotated textual data that maps into the evoked frames, are important for several NLP tasks. However, they are expensive to build and, consequently, are unavailable for many languages and domains. Thus, approaches able to induce semantic frames in an unsupervised manner are highly valuable. In this paper we approach that task from a network perspective as a community detection problem that targets the identification of groups of verb instances that evoke the same semantic frame and verb arguments that play the same semantic role. To do so, we apply a graph-clustering algorithm to a graph with contextualized representations of verb instances or arguments as nodes connected by edges if the distance between them is below a threshold that defines the granularity of the induced frames. By applying this approach to the benchmark dataset defined in the context of SemEval 2019, we outperformed all of the previous approaches to the task, achieving the current state-of-the-art performance.Springer Nature2021-01-15T14:43:06Z2020-01-01T00:00:00Z20202021-01-15T14:38:51Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10071/21299eng2364-822810.1007/s41109-020-00312-zRibeiro, E.Teixeira, A. S.Ribeiro, R.De Matos, D. M.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-11-09T17:54:18Zoai:repositorio.iscte-iul.pt:10071/21299Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:27:20.594220Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Semantic frame induction through the detection of communities of verbs and their arguments |
title |
Semantic frame induction through the detection of communities of verbs and their arguments |
spellingShingle |
Semantic frame induction through the detection of communities of verbs and their arguments Ribeiro, E. Semantic frames Semantic roles Contextualized representations Community detection Graph clustering |
title_short |
Semantic frame induction through the detection of communities of verbs and their arguments |
title_full |
Semantic frame induction through the detection of communities of verbs and their arguments |
title_fullStr |
Semantic frame induction through the detection of communities of verbs and their arguments |
title_full_unstemmed |
Semantic frame induction through the detection of communities of verbs and their arguments |
title_sort |
Semantic frame induction through the detection of communities of verbs and their arguments |
author |
Ribeiro, E. |
author_facet |
Ribeiro, E. Teixeira, A. S. Ribeiro, R. De Matos, D. M. |
author_role |
author |
author2 |
Teixeira, A. S. Ribeiro, R. De Matos, D. M. |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Ribeiro, E. Teixeira, A. S. Ribeiro, R. De Matos, D. M. |
dc.subject.por.fl_str_mv |
Semantic frames Semantic roles Contextualized representations Community detection Graph clustering |
topic |
Semantic frames Semantic roles Contextualized representations Community detection Graph clustering |
description |
Resources such as FrameNet, which provide sets of semantic frame definitions and annotated textual data that maps into the evoked frames, are important for several NLP tasks. However, they are expensive to build and, consequently, are unavailable for many languages and domains. Thus, approaches able to induce semantic frames in an unsupervised manner are highly valuable. In this paper we approach that task from a network perspective as a community detection problem that targets the identification of groups of verb instances that evoke the same semantic frame and verb arguments that play the same semantic role. To do so, we apply a graph-clustering algorithm to a graph with contextualized representations of verb instances or arguments as nodes connected by edges if the distance between them is below a threshold that defines the granularity of the induced frames. By applying this approach to the benchmark dataset defined in the context of SemEval 2019, we outperformed all of the previous approaches to the task, achieving the current state-of-the-art performance. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01T00:00:00Z 2020 2021-01-15T14:43:06Z 2021-01-15T14:38:51Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10071/21299 |
url |
http://hdl.handle.net/10071/21299 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2364-8228 10.1007/s41109-020-00312-z |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Springer Nature |
publisher.none.fl_str_mv |
Springer Nature |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134836149977088 |