Explicating the Implicit: Argument Detection Beyond Sentence Boundaries

Paul Roit, Aviv Slobodkin, Eran Hirsch, Arie Cattan, Ayal Klein, Valentina Pyatkin, Ido Dagan


Abstract
Detecting semantic arguments of a predicate word has been conventionally modeled as a sentence-level task. The typical reader, however, perfectly interprets predicate-argument relations in a much wider context than just the sentence where the predicate was evoked. In this work, we reformulate the problem of argument detection through textual entailment to capture semantic relations across sentence boundaries. We propose a method that tests whether some semantic relation can be inferred from a full passage by first encoding it into a simple and standalone proposition and then testing for entailment against the passage. Our method does not require direct supervision, which is generally absent due to dataset scarcity, but instead builds on existing NLI and sentence-level SRL resources. Such a method can potentially explicate pragmatically understood relations into a set of explicit sentences. We demonstrate it on a recent document-level benchmark, outperforming some supervised methods and contemporary language models.
Anthology ID:
2024.acl-long.863
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16394–16409
Language:
URL:
https://aclanthology.org/2024.acl-long.863
DOI:
10.18653/v1/2024.acl-long.863
Bibkey:
Cite (ACL):
Paul Roit, Aviv Slobodkin, Eran Hirsch, Arie Cattan, Ayal Klein, Valentina Pyatkin, and Ido Dagan. 2024. Explicating the Implicit: Argument Detection Beyond Sentence Boundaries. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16394–16409, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Explicating the Implicit: Argument Detection Beyond Sentence Boundaries (Roit et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.acl-long.863.pdf