Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction

Bowen Yu, Xue Mengge, Zhenyu Zhang, Tingwen Liu, Wang Yubin, Bin Wang


Abstract
Dependency trees have been shown to be effective in capturing long-range relations between target entities. Nevertheless, how to selectively emphasize target-relevant information and remove irrelevant content from the tree is still an open problem. Existing approaches employing pre-defined rules to eliminate noise may not always yield optimal results due to the complexity and variability of natural language. In this paper, we present a novel architecture named Dynamically Pruned Graph Convolutional Network (DP-GCN), which learns to prune the dependency tree with rethinking in an end-to-end scheme. In each layer of DP-GCN, we employ a selection module to concentrate on nodes expressing the target relation by a set of binary gates, and then augment the pruned tree with a pruned semantic graph to ensure the connectivity. After that, we introduce a rethinking mechanism to guide and refine the pruning operation by feeding back the high-level learned features repeatedly. Extensive experimental results demonstrate that our model achieves impressive results compared to strong competitors.
Anthology ID:
2020.coling-main.341
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
3842–3852
Language:
URL:
https://aclanthology.org/2020.coling-main.341
DOI:
10.18653/v1/2020.coling-main.341
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.341.pdf
Data
TACRED