IBEnt: Chemical Entity Mentions in Patents using ChEBI

This article presents our approach to the CEMP task of BioCreative V.5, which consisted in using our system, IBEnt, to identify chemical entity mentions in patents through machine learning and semantic similarity techniques. The features used combine the results of a CRF classifier, two lexical matching methods (FiGO and MER) and semantic similarity measures on ChEBI ontology. We also tested the usage of MER by itself, without the machine learning approach. Combining these techniques, we submitted 5 runs for evaluation. We obtained better results using the machine learning approach with lexical and semantic similarity features. The best F-score obtained was 0.8541, while the MER system obtained 0.5967.