End to End Chinese Lexical Fusion Recognition with Sememe Knowledge

Yijiang Liu, Meishan Zhang, Donghong Ji


Abstract
In this paper, we present Chinese lexical fusion recognition, a new task which could be regarded as one kind of coreference recognition. First, we introduce the task in detail, showing the relationship with coreference recognition and differences from the existing tasks. Second, we propose an end-to-end model for the task, handling mentions as well as coreference relationship jointly. The model exploits the state-of-the-art contextualized BERT representations as an encoder, and is further enhanced with the sememe knowledge from HowNet by graph attention networks. We manually annotate a benchmark dataset for the task and then conduct experiments on it. Results demonstrate that our final model is effective and competitive for the task. Detailed analysis is offered for comprehensively understanding the new task and our proposed model.
Anthology ID:
2020.coling-main.263
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2935–2946
Language:
URL:
https://aclanthology.org/2020.coling-main.263
DOI:
10.18653/v1/2020.coling-main.263
Bibkey:
Cite (ACL):
Yijiang Liu, Meishan Zhang, and Donghong Ji. 2020. End to End Chinese Lexical Fusion Recognition with Sememe Knowledge. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2935–2946, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
End to End Chinese Lexical Fusion Recognition with Sememe Knowledge (Liu et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.263.pdf