Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
This work addresses relation extraction for natural language processing by improving efficiency and accuracy over existing dependency-based models, though it is incremental as it builds on graph convolutional networks.
The paper tackled the problem of relation extraction by proposing a graph convolutional network extension that efficiently pools information over dependency trees with a novel pruning strategy, achieving state-of-the-art performance on the TACRED dataset and showing complementary strengths when combined with sequence models.
Dependency trees help relation extraction models capture long-range relations between words. However, existing dependency-based models either neglect crucial information (e.g., negation) by pruning the dependency trees too aggressively, or are computationally inefficient because it is difficult to parallelize over different tree structures. We propose an extension of graph convolutional networks that is tailored for relation extraction, which pools information over arbitrary dependency structures efficiently in parallel. To incorporate relevant information while maximally removing irrelevant content, we further apply a novel pruning strategy to the input trees by keeping words immediately around the shortest path between the two entities among which a relation might hold. The resulting model achieves state-of-the-art performance on the large-scale TACRED dataset, outperforming existing sequence and dependency-based neural models. We also show through detailed analysis that this model has complementary strengths to sequence models, and combining them further improves the state of the art.