# Graph Convolution over Pruned Dependency Trees Improves Relation Extraction

arXiv: https://arxiv.org/abs/1809.10185 · HTML: https://mlsanity.com/paper/1809.10185/

## Key facts

- Cited by 146 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2018.

## Built on by (most cited first, 30 of 146)

- [QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering](https://mlsanity.com/paper/2104.06378/) (2021)
- [PTR: Prompt Tuning with Rules for Text Classification](https://mlsanity.com/paper/2105.11259/) (2021)
- [KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction](https://mlsanity.com/paper/2104.07650/) (2021)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [An Improved Baseline for Sentence-level Relation Extraction](https://mlsanity.com/paper/2102.01373/) (2021)
- [Re-TACRED: Addressing Shortcomings of the TACRED Dataset](https://mlsanity.com/paper/2104.08398/) (2021)
- [BertGCN: Transductive Text Classification by Combining GCN and BERT](https://mlsanity.com/paper/2105.05727/) (2021)
- [Accelerating Large Scale Real-Time GNN Inference using Channel Pruning](https://mlsanity.com/paper/2105.04528/) (2021)
- [Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation](https://mlsanity.com/paper/2203.10900/) (2022)
- [Learning Rich Representation of Keyphrases from Text](https://mlsanity.com/paper/2112.08547/) (2021)
- [Learning from Noisy Labels for Entity-Centric Information Extraction](https://mlsanity.com/paper/2104.08656/) (2021)
- [A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition](https://mlsanity.com/paper/2106.14373/) (2021)
- [Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge](https://mlsanity.com/paper/2105.02520/) (2021)
- [Relation Classification with Entity Type Restriction](https://mlsanity.com/paper/2105.08393/) (2021)
- [Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis](https://mlsanity.com/paper/2205.03784/) (2022)
- [Revisiting Large Language Models as Zero-shot Relation Extractors](https://mlsanity.com/paper/2310.05028/) (2023)
- [Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes](https://mlsanity.com/paper/2104.08481/) (2021)
- [Context versus Prior Knowledge in Language Models](https://mlsanity.com/paper/2404.04633/) (2024)
- [A Survey on Extraction of Causal Relations from Natural Language Text](https://mlsanity.com/paper/2101.06426/) (2021)
- [Discriminative Reasoning for Document-level Relation Extraction](https://mlsanity.com/paper/2106.01562/) (2021)
- [Better Feature Integration for Named Entity Recognition](https://mlsanity.com/paper/2104.05316/) (2021)
- [A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers](https://mlsanity.com/paper/2306.02051/) (2023)
- [Uncovering Main Causalities for Long-tailed Information Extraction](https://mlsanity.com/paper/2109.05213/) (2021)
- [Does Recommend-Revise Produce Reliable Annotations? An Analysis on Missing Instances in DocRED](https://mlsanity.com/paper/2204.07980/) (2022)
- [Unified Semantic Typing with Meaningful Label Inference](https://mlsanity.com/paper/2205.01826/) (2022)
- [Entity-centered Cross-document Relation Extraction](https://mlsanity.com/paper/2210.16541/) (2022)
- [DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population](https://mlsanity.com/paper/2201.03335/) (2022)
- [Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction](https://mlsanity.com/paper/2106.01793/) (2021)
- [Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling](https://mlsanity.com/paper/2305.11719/) (2023)
- [Learning Logic Rules for Document-level Relation Extraction](https://mlsanity.com/paper/2111.05407/) (2021)

## Abstract (arXiv)

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.