Cross-Sentence N-ary Relation Extraction with Graph LSTMs

TL;DR

This paper introduces a graph LSTM-based framework for extracting complex n-ary relations across multiple sentences, improving knowledge base construction in precision medicine through enhanced accuracy and multi-task learning.

Contribution

The paper presents a novel graph LSTM approach for cross-sentence n-ary relation extraction, integrating various linguistic dependencies and enabling multi-task learning.

Findings

Cross-sentence extraction increased knowledge base size.

Multi-task learning improved extraction accuracy.

Linguistic analysis impacts extraction performance.

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.