Cross-Sentence N-ary Relation Extraction with Graph LSTMs

Abstract

Past work in relation extraction has focused on binary relations in single sentences. Recent NLP inroads in high-value domains have sparked interest in the more general setting of extracting n-ary relations that span multiple sentences. In this paper, we explore a general relation extraction framework based on graph long short-term memory networks (graph LSTMs) that can be easily extended to cross-sentence n-ary relation extraction. The graph formulation provides a unified way of exploring different LSTM approaches and incorporating various intra-sentential and inter-sentential dependencies, such as sequential, syntactic, and discourse relations. A robust contextual representation is learned for the entities, which serves as input to the relation classifier. This simplifies handling of relations with arbitrary arity, and enables multi-task learning with related relations. We evaluate this framework in two important precision medicine settings, demonstrating its effectiveness with both conventional supervised learning and distant supervision. Cross-sentence extraction produced larger knowledge bases. and multi-task learning significantly improved extraction accuracy. A thorough analysis of various LSTM approaches yielded useful insight the impact of linguistic analysis on extraction accuracy.

Conditional accepted by TACL in December 2016; published in April 2017; presented at ACL in August 2017

References in corpus (4)

• End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures
• Classifying Relations by Ranking with Convolutional Neural Networks
• Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Path
• Improving Named Entity Recognition for Chinese Social Media with Word Segmentation Representation Learning

Cited by in corpus (17)

• DeepGCNs: Making GCNs Go as Deep as CNNs
• On the Explainability of Natural Language Processing Deep Models
• Machine Knowledge: Creation and Curation of Comprehensive Knowledge Bases
• COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation
• Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
• Representation Learning for Natural Language Processing
• Deep Neural Approaches to Relation Triplets Extraction: A Comprehensive Survey
• Comparison of biomedical relationship extraction methods and models for knowledge graph creation
• From POS tagging to dependency parsing for biomedical event extraction
• Extracting Entities of Interest from Comparative Product Reviews
• Attention-Based Capsule Networks with Dynamic Routing for Relation Extraction
• PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
• ETH-DS3Lab at SemEval-2018 Task 7: Effectively Combining Recurrent and Convolutional Neural Networks for Relation Classification and Extraction
• Multi-Attribute Relation Extraction (MARE) -- Simplifying the Application of Relation Extraction
• Weight Annotation in Information Extraction
• Graph Convolution for Multimodal Information Extraction from Visually Rich Documents
• DeepDrawing: A Deep Learning Approach to Graph Drawing