Grounding the Lexical Substitution Task in Entailment

Talgat Omarov, Grzegorz Kondrak


Abstract
Existing definitions of lexical substitutes are often vague or inconsistent with the gold annotations. We propose a new definition which is grounded in the relation of entailment; namely, that the sentence that results from the substitution should be in the relation of mutual entailment with the original sentence. We argue that the new definition is well-founded and supported by previous work on lexical entailment. We empirically validate our definition by verifying that it covers the majority of gold substitutes in existing datasets. Based on this definition, we create a new dataset from existing semantic resources. Finally, we propose a novel context augmentation method motivated by the definition, which relates the substitutes to the sense of the target word by incorporating glosses and synonyms directly into the context. Experimental results demonstrate that our augmentation approach improves the performance of lexical substitution systems on the existing benchmarks.
Anthology ID:
2023.findings-acl.179
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2854–2869
Language:
URL:
https://aclanthology.org/2023.findings-acl.179
DOI:
10.18653/v1/2023.findings-acl.179
Bibkey:
Cite (ACL):
Talgat Omarov and Grzegorz Kondrak. 2023. Grounding the Lexical Substitution Task in Entailment. In Findings of the Association for Computational Linguistics: ACL 2023, pages 2854–2869, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Grounding the Lexical Substitution Task in Entailment (Omarov & Kondrak, Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.179.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.179.mp4