RelU-Net: Syntax-aware Graph U-Net for Relational Triple Extraction

Yunqi Zhang, Yubo Chen, Yongfeng Huang


Abstract
Relational triple extraction is a critical task for natural language processing. Existing methods mainly focused on capturing semantic information, but suffered from ignoring the syntactic structure of the sentence, which is proved in the relation classification task to contain rich relational information. This is due to the absence of entity locations, which is the prerequisite for pruning noisy edges from the dependency tree, when extracting relational triples. In this paper, we propose a unified framework to tackle this challenge and incorporate syntactic information for relational triple extraction. First, we propose to automatically contract the dependency tree into a core relational topology and eliminate redundant information with graph pooling operations. Then, we propose a symmetrical expanding path with graph unpooling operations to fuse the contracted core syntactic interactions with the original sentence context. We also propose a bipartite graph matching objective function to capture the reflections between the core topology and golden relational facts. Since our model shares similar contracting and expanding paths with encoder-decoder models like U-Net, we name our model as Relation U-Net (RelU-Net). We conduct experiments on several datasets and the results prove the effectiveness of our method.
Anthology ID:
2022.emnlp-main.282
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4208–4217
Language:
URL:
https://aclanthology.org/2022.emnlp-main.282
DOI:
10.18653/v1/2022.emnlp-main.282
Bibkey:
Cite (ACL):
Yunqi Zhang, Yubo Chen, and Yongfeng Huang. 2022. RelU-Net: Syntax-aware Graph U-Net for Relational Triple Extraction. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4208–4217, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
RelU-Net: Syntax-aware Graph U-Net for Relational Triple Extraction (Zhang et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.282.pdf