%0 Conference Paper %1 peng2017crosssentence %A Peng, Nanyun %A Poon, Hoifung %A Quirk, Chris %A Toutanova, Kristina %A Yih, Wen-tau %B ACL %D 2017 %K extraction graph lstm network neural pubmed relation %T Cross-Sentence N-ary Relation Extraction with Graph LSTMs %U http://arxiv.org/abs/1708.03743 %X 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.

@inproceedings{peng2017crosssentence, 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.}, added-at = {2018-07-02T13:17:31.000+0200}, author = {Peng, Nanyun and Poon, Hoifung and Quirk, Chris and Toutanova, Kristina and Yih, Wen-tau}, biburl = {https://www.bibsonomy.org/bibtex/2579fb969679799515b8f72bc7c751bb0/schwemmlein}, booktitle = {ACL}, description = {Cross-Sentence N-ary Relation Extraction with Graph LSTMs}, interhash = {a8d8870408d4b2df4b06001e1723ec2e}, intrahash = {579fb969679799515b8f72bc7c751bb0}, keywords = {extraction graph lstm network neural pubmed relation}, note = {cite arxiv:1708.03743Comment: Conditional accepted by TACL in December 2016; published in April 2017; presented at ACL in August 2017}, timestamp = {2018-07-02T13:17:31.000+0200}, title = {Cross-Sentence N-ary Relation Extraction with Graph LSTMs}, url = {http://arxiv.org/abs/1708.03743}, year = 2017 }