Word-level Prefix/Suffix Sense Detection: A Case Study on Negation Sense with Few-shot Learning

Yameng Li, Zicheng Li, Ying Chen, Shoushan Li


Abstract
Morphological analysis is an important research issue in the field of natural language processing. In this study, we propose a context-free morphological analysis task, namely word-level prefix/suffix sense detection, which deals with the ambiguity of sense expressed by prefix/suffix. To research this novel task, we first annotate a corpus with prefixes/suffixes expressing negation (e.g., il-, un-, -less) and then propose a novel few-shot learning approach that applies an input-augmentation prompt to a token-replaced detection pre-training model. Empirical studies demonstrate the effectiveness of the proposed approach to word-level prefix/suffix negation sense detection.
Anthology ID:
2023.findings-acl.484
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:
7651–7658
Language:
URL:
https://aclanthology.org/2023.findings-acl.484
DOI:
10.18653/v1/2023.findings-acl.484
Bibkey:
Cite (ACL):
Yameng Li, Zicheng Li, Ying Chen, and Shoushan Li. 2023. Word-level Prefix/Suffix Sense Detection: A Case Study on Negation Sense with Few-shot Learning. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7651–7658, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Word-level Prefix/Suffix Sense Detection: A Case Study on Negation Sense with Few-shot Learning (Li et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.findings-acl.484.pdf