Paper: What causes a causal relation? Detecting Causal Triggers in Biomedical Scientific Discourse

ACL ID P13-3006
Title What causes a causal relation? Detecting Causal Triggers in Biomedical Scientific Discourse
Venue Annual Meeting of the Association of Computational Linguistics
Session Student Session
Year 2013
Authors

Current domain-specific information extrac- tion systems represent an important resource for biomedical researchers, who need to pro- cess vaster amounts of knowledge in short times. Automatic discourse causality recog- nition can further improve their workload by suggesting possible causal connections and aiding in the curation of pathway models. We here describe an approach to the automatic identification of discourse causality triggers in the biomedical domain using machine learn- ing. We create several baselines and experi- ment with various parameter settings for three algorithms, i.e., Conditional Random Fields (CRF), Support Vector Machines (SVM) and Random Forests (RF). Also, we evaluate the impact of lexical, syntactic and semantic fea- tures on each of the algorithms and look at ...