Semantic frame induction through the detection of communities of verbs and their arguments

Applied Network Science

Andreia Sofia Teixeira¹  Eugénio Ribeiro²  David Martins de Matos²  Ricardo Ribeiro³ 

[1] INESC-ID, Lisboa, Portugal;Center for Social and Biomedical Complexity, School of Informatics, Computing, & Engineering, Indiana University, Bloomington, Indiana, USA;Indiana University Network Science Institute (IUNI), Indiana University, Bloomington, Indiana, USA;INESC-ID, Lisboa, Portugal;Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal;INESC-ID, Lisboa, Portugal;Instituto Universitário de Lisboa (ISCTE-IUL), Lisboa, Portugal;

关键词: Semantic frames;    Semantic roles;    Contextualized representations;    Community detection;    Graph clustering;   

DOI  :  10.1007/s41109-020-00312-z

来源: Springer

【 摘 要 】

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.

【 授权许可】

CC BY