Paper: Exploring a Probabilistic Earley Parser for Event Composition in Biomedical Texts

ACL ID W13-2019
Title Exploring a Probabilistic Earley Parser for Event Composition in Biomedical Texts
Venue Proceedings of the BioNLP Shared Task 2013 Workshop
Session
Year 2013
Authors

We describe a high precision system for ex- tracting events of biomedical significance that was developed during the BioNLP shared task 2013 and tested on the Cancer Genetics data set. The system achieved an F-score on the de- velopment data of 73.67 but was ranked 5th out of six with an F-score of 29.94 on the test data. However, precision was the second highest ranked on the task at 62.73. Analysis suggests the need to continue to improve our system for complex events particularly taking into ac- count cross-domain differences in argument distributions.