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

Md Faisal Mahbub Chowdhury, Alberto Lavelli

Abstract: 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.