Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
arXiv:1809.10185
Abstract
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.
EMNLP 2018. Code available at: https://github.com/qipeng/gcn-over-pruned-trees
Cited by in corpus (13)
- Graph Neural Networks: A Review of Methods and Applications
- MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
- GraphIE: A Graph-Based Framework for Information Extraction
- Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
- Accelerating Large Scale Real-Time GNN Inference using Channel Pruning
- A Frustratingly Easy Approach for Entity and Relation Extraction
- Structural block driven - enhanced convolutional neural representation for relation extraction
- Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering
- Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension
- Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP
- NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction
- Machine Learning Applications for Therapeutic Tasks with Genomics Data
- On the Effectiveness of the Pooling Methods for Biomedical Relation Extraction with Deep Learning