Cross-Sentence N-ary Relation Extraction with Graph LSTMs

Abstract

Past work in relation extraction focuses on binary relations in single sentences. Recent NLP inroads in high-valued domains have kindled strong 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 (graph LSTM), which can be easily extended to cross-sentence n-ary relation extraction. The graph formulation provides a unifying way to explore different LSTM approaches and incorporate 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, making it easy for scaling to arbitrary relation arity n, as well as for multi-task learning with related relations. We evaluated this framework in two important domains in precision medicine and demonstrated its effectiveness with both supervised learning and distant supervision. Cross-sentence extraction produced far more knowledge, and multi-task learning significantly improved extraction accuracy. A thorough analysis comparing various LSTM approaches yielded interesting insight on how linguistic analysis impacts the performance.