L2F/INESC-ID at SemEval-2019 Task 2: Unsupervised Lexical Semantic Frame Induction using Contextualized Word Representations

Eugénio Ribeiro, Vânia Mendonça, Ricardo Ribeiro, David Martins de Matos, Alberto Sardinha, Ana Lúcia Santos, Luísa Coheur


Abstract
Building large datasets annotated with semantic information, such as FrameNet, is an expensive process. Consequently, such resources are unavailable for many languages and specific domains. This problem can be alleviated by using unsupervised approaches to induce the frames evoked by a collection of documents. That is the objective of the second task of SemEval 2019, which comprises three subtasks: clustering of verbs that evoke the same frame and clustering of arguments into both frame-specific slots and semantic roles. We approach all the subtasks by applying a graph clustering algorithm on contextualized embedding representations of the verbs and arguments. Using such representations is appropriate in the context of this task, since they provide cues for word-sense disambiguation. Thus, they can be used to identify different frames evoked by the same words. Using this approach we were able to outperform all of the baselines reported for the task on the test set in terms of Purity F1, as well as in terms of BCubed F1 in most cases.
Anthology ID:
S19-2019
Volume:
Proceedings of the 13th International Workshop on Semantic Evaluation
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota, USA
Editors:
Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
Venue:
SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
130–136
Language:
URL:
https://aclanthology.org/S19-2019
DOI:
10.18653/v1/S19-2019
Bibkey:
Cite (ACL):
Eugénio Ribeiro, Vânia Mendonça, Ricardo Ribeiro, David Martins de Matos, Alberto Sardinha, Ana Lúcia Santos, and Luísa Coheur. 2019. L2F/INESC-ID at SemEval-2019 Task 2: Unsupervised Lexical Semantic Frame Induction using Contextualized Word Representations. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 130–136, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
Cite (Informal):
L2F/INESC-ID at SemEval-2019 Task 2: Unsupervised Lexical Semantic Frame Induction using Contextualized Word Representations (Ribeiro et al., SemEval 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/autopr/S19-2019.pdf
Data
FrameNet