DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Parsing

Bin Li, Miao Gao, Yunlong Fan, Yikemaiti Sataer, Zhiqiang Gao, Yaocheng Gui


Abstract
A recent success in semantic dependency parsing shows that graph neural networks can make significant accuracy improvements, owing to its powerful ability in learning expressive graph representations. However, this work learns graph representations based on a static graph constructed by an existing parser, suffering from two drawbacks: (1) the static graph might be error-prone (e.g., noisy or incomplete), and (2) graph construction stage and graph representation learning stage are disjoint, the errors introduced in the graph construction stage cannot be corrected and might be accumulated to later stages. To address these two drawbacks, we propose a dynamic graph learning framework and apply it to semantic dependency parsing, for jointly learning graph structure and graph representations. Experimental results show that our parser outperforms the previous parsers on the SemEval-2015 Task 18 dataset in three languages (English, Chinese, and Czech).
Anthology ID:
2022.coling-1.351
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3994–4004
Language:
URL:
https://aclanthology.org/2022.coling-1.351
DOI:
Bibkey:
Cite (ACL):
Bin Li, Miao Gao, Yunlong Fan, Yikemaiti Sataer, Zhiqiang Gao, and Yaocheng Gui. 2022. DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Parsing. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3994–4004, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Parsing (Li et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.351.pdf
Code
 libinnlp/dyngl-sdp