Paper: Extracting Gene Regulation Networks Using Linear-Chain Conditional Random Fields and Rules

ACL ID W13-2026
Title Extracting Gene Regulation Networks Using Linear-Chain Conditional Random Fields and Rules
Venue Proceedings of the BioNLP Shared Task 2013 Workshop
Session
Year 2013
Authors

Published literature in molecular genetics may collectively provide much informa- tion on gene regulation networks. Ded- icated computational approaches are re- quired to sip through large volumes of text and infer gene interactions. We propose a novel sieve-based relation extraction sys- tem that uses linear-chain conditional ran- dom fields and rules. Also, we intro- duce a new skip-mention data represen- tation to enable distant relation extraction using first-order models. To account for a variety of relation types, multiple models are inferred. The system was applied to the BioNLP 2013 Gene Regulation Network Shared Task. Our approach was ranked first of five, with a slot error rate of 0.73.