Enhancing Language Representation with Constructional Information for Natural Language Understanding

Lvxiaowei Xu, Jianwang Wu, Jiawei Peng, Zhilin Gong, Ming Cai, Tianxiang Wang


Abstract
Natural language understanding (NLU) is an essential branch of natural language processing, which relies on representations generated by pre-trained language models (PLMs). However, PLMs primarily focus on acquiring lexico-semantic information, while they may be unable to adequately handle the meaning of constructions. To address this issue, we introduce construction grammar (CxG), which highlights the pairings of form and meaning, to enrich language representation. We adopt usage-based construction grammar as the basis of our work, which is highly compatible with statistical models such as PLMs. Then a HyCxG framework is proposed to enhance language representation through a three-stage solution. First, all constructions are extracted from sentences via a slot-constraints approach. As constructions can overlap with each other, bringing redundancy and imbalance, we formulate the conditional max coverage problem for selecting the discriminative constructions. Finally, we propose a relational hypergraph attention network to acquire representation from constructional information by capturing high-order word interactions among constructions. Extensive experiments demonstrate the superiority of the proposed model on a variety of NLU tasks.
Anthology ID:
2023.acl-long.258
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4685–4705
Language:
URL:
https://aclanthology.org/2023.acl-long.258
DOI:
10.18653/v1/2023.acl-long.258
Bibkey:
Cite (ACL):
Lvxiaowei Xu, Jianwang Wu, Jiawei Peng, Zhilin Gong, Ming Cai, and Tianxiang Wang. 2023. Enhancing Language Representation with Constructional Information for Natural Language Understanding. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4685–4705, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Enhancing Language Representation with Constructional Information for Natural Language Understanding (Xu et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.258.pdf
Video:
 https://preview.aclanthology.org/add_acl24_videos/2023.acl-long.258.mp4