Semantic Frame Induction as a Community Detection Problem

• Type: Article in International Conference Proceedings Book
• Date: 2019

Authors

Ribeiro, E (Author) Other; Teixeira, AS (Author) Other; Ribeiro, R (Author) Other; de Matos, DM (Author) Other

Conference proceedings International

Title: Complex Networks and Their Applications VIII - Volume 1 Proceedings of the Eighth International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2019, Lisbon, Portugal, December 10-12, 2019.

Pages: 274-285

8th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2019

10 December 2019 through 12 December 2019

Indexing

Scopus - 1 Citation

Other information

Authenticus ID: P-00R-CJB

DOI: 10.1007/978-3-030-36687-2_23

Abstract (EN): Resources such as FrameNet provide semantic information that is important for multiple 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. To do so, we apply a graph-clustering algorithm to a graph with contextualized representations of verb instances as nodes connected by an edge 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 the SemEval shared task we outperformed all the previous approaches to the task. © 2020, Springer Nature Switzerland AG.

Language: English

Type (Professor's evaluation): Scientific