Entity-Focused Sentence Simplification for Relation Extraction

Relations between entities in text have been widely researched in the natural language processing and informationextraction communities. The region connecting a pair of entities (in a parsed sentence) is often used to construct kernels or feature vectors that can recognize and extract interesting relations. Such regions are useful, but they can also incorporate unnecessary distracting information. In this paper, we propose a rulebased method to remove the information that is unnecessary for relation extraction. Protein–protein interaction (PPI) is used as an example relation extraction problem. A dozen simple rules are defined on output from a deep parser. Each rule specifically examines the entities in one target interaction pair. These simple rules were tested using several PPI corpora. The PPI extraction performance was improved on all the PPI corpora.