HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection

Zheng Chu, Ziqing Yang, Yiming Cui, Zhigang Chen, Ming Liu


Abstract
The same multi-word expressions may have different meanings in different sentences. They can be mainly divided into two categories, which are literal meaning and idiomatic meaning. Non-contextual-based methods perform poorly on this problem, and we need contextual embedding to understand the idiomatic meaning of multi-word expressions correctly. We use a pre-trained language model, which can provide a context-aware sentence embedding, to detect whether multi-word expression in the sentence is idiomatic usage.
Anthology ID:
2022.semeval-1.28
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Venues:
NAACL | SemEval
SIGs:
SIGSEM | SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
221–227
Language:
URL:
https://aclanthology.org/2022.semeval-1.28
DOI:
10.18653/v1/2022.semeval-1.28
Bibkey:
Cite (ACL):
Zheng Chu, Ziqing Yang, Yiming Cui, Zhigang Chen, and Ming Liu. 2022. HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 221–227, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
HIT at SemEval-2022 Task 2: Pre-trained Language Model for Idioms Detection (Chu et al., SemEval 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.semeval-1.28.pdf