Paper: IRISA participation to BioNLP-ST13: lazy-learning and information retrieval for information extraction tasks

ACL ID W13-2027
Title IRISA participation to BioNLP-ST13: lazy-learning and information retrieval for information extraction tasks
Venue Proceedings of the BioNLP Shared Task 2013 Workshop
Session
Year 2013
Authors

This paper describes the information extraction techniques developed in the framework of the participation of IRISA- TexMex to the following BioNLP-ST13 tasks: Bacterial Biotope subtasks 1 and 2, and Graph Regulation Network. The approaches developed are general-purpose ones and do not rely on specialized pre- processing, nor specialized external data, and they are expected to work indepen- dently of the domain of the texts pro- cessed. They are classically based on ma- chine learning techniques, but we put the emphasis on the use of similarity mea- sures inherited from the information re- trieval domain (Okapi-BM25 (Robertson et al., 1998), language modeling (Hiem- stra, 1998)). Through the good results ob- tained for these tasks, we show that these simple settings are competitive provide...