Skip navigation
User training | Reference and search service

Library catalog

Content aggregators
Please use this identifier to cite or link to this item:

Title: Semantic frame induction through the detection of communities of verbs and their arguments
Authors: Ribeiro, E.
Teixeira, A. S.
Ribeiro, R.
De Matos, D. M.
Keywords: Semantic frames
Semantic roles
Contextualized representations
Community detection
Graph clustering
Issue Date: 2020
Publisher: Springer Nature
Abstract: 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.
Peer reviewed: yes
DOI: 10.1007/s41109-020-00312-z
ISSN: 2364-8228
Appears in Collections:CTI-RI - Artigos em revistas científicas internacionais com arbitragem científica

Files in This Item:
File Description SizeFormat 
2020 [Ribeiro] Semantic frame induction through the detection of communities of verbs and their arguments.pdfVersão Editora2.12 MBAdobe PDFView/Open

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Currículo DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.