Exploiting the Scope of Negations and Heterogeneous Features for Relation Extraction: A Case Study for Drug-Drug Interaction Extraction

Md. Faisal Mahbub Chowdhury and Alberto Lavelli

This paper presents an approach that exploits the scope of negation cues for relation extraction (RE) without the need of using any specifically annotated dataset for building a separate negation scope detection classifier. New features are proposed which are used in two different stages. These also include non-target entity specific features. The proposed RE approach outperforms the previous state of the art for drug-drug interaction (DDI) extraction