Paper: Extracting Biomedical Events and Modifications Using Subgraph Matching with Noisy Training Data

ACL ID W13-2005
Title Extracting Biomedical Events and Modifications Using Subgraph Matching with Noisy Training Data
Venue Proceedings of the BioNLP Shared Task 2013 Workshop
Session
Year 2013
Authors

The Genia Event (GE) extraction task of the BioNLP Shared Task addresses the ex- traction of biomedical events from the nat- ural language text of the published litera- ture. In our submission, we modified an existing system for learning of event pat- terns via dependency parse subgraphs to utilise a more accurate parser and signifi- cantly more, but noisier, training data. We explore the impact of these two aspects of the system and conclude that the change in parser limits recall to an extent that cannot be offset by the large quantities of training data. However, our extensions of the sys- tem to extract modification events shows promise.