Paper: RankPref: Ranking Sentences Describing Relations between Biomedical Entities with an Application

ACL ID W12-2420
Title RankPref: Ranking Sentences Describing Relations between Biomedical Entities with an Application
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2012
Authors

This paper presents a machine learning ap- proach that selects and, more generally, ranks sentences containing clear relations between genes and terms that are related to them. This is treated as a binary classification task, where preference judgments are used to learn how to choose a sentence from a pair of sentences. Features to capture how the relationship is de- scribed textually, as well as how central the relationship is in the sentence, are used in the learning process. Simplification of complex sentences into simple structures is also applied for the extraction of the features. We show that such simplification improves the results by up to 13%. We conducted three different evalu- ations and we found that the system signifi- cantly outperforms the baselines.