Utilize este identificador para referenciar este registo:
http://hdl.handle.net/10071/21299
Autoria: | Ribeiro, E. Teixeira, A. S. Ribeiro, R. De Matos, D. M. |
Data: | 2020 |
Título próprio: | Semantic frame induction through the detection of communities of verbs and their arguments |
Volume: | 5 |
Número: | 1 |
ISSN: | 2364-8228 |
DOI (Digital Object Identifier): | 10.1007/s41109-020-00312-z |
Palavras-chave: | Semantic frames Semantic roles Contextualized representations Community detection Graph clustering |
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. |
Arbitragem científica: | yes |
Acesso: | Acesso Aberto |
Aparece nas coleções: | CTI-RI - Artigos em revistas científicas internacionais com arbitragem científica |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
2020 [Ribeiro] Semantic frame induction through the detection of communities of verbs and their arguments.pdf | Versão Editora | 2,12 MB | Adobe PDF | Ver/Abrir |
Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.