Entity-Focused Sentence Simplification for Relation Extraction

Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010), pages 788–796, Beijing, August 2010 Entity-Focused Sentence Simplification for Relation Extraction Makoto Miwa1 Rune Sætre1 Yusuke Miyao2 Jun’ichi Tsujii1,3,4 1Department of Computer Science, The University of Tokyo 2National Institute of Informatics 3School of Computer Science, University of Manchester 4National Center for Text Mining mmiwa@is.s.u-tokyo.ac.jp,rune.saetre@is.s.u-tokyo.ac.jp, yusuke@nii.ac.jp,tsujii@is.s.u-tokyo.ac.jp Abstract Relations between entities in text have been widely researched in the natu- ral language processing and information- extraction communities. The region con- necting a pair of entities (in a parsed sentence) is often used to construct ker- nels or feature vectors that can recognize and extract interesting relations. Such re- gions are useful, but they can also incor- porate unnecessary distracting informa- tion. In this paper, we propose a rule- based 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 out- put from a deep parser. Each rule specif- ically 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. 1 Introduction Relation extraction (RE) is the task of finding a relevant semantic relation between two given tar- get entities in a sentence (Sarawagi, 2008). Some example relation types are person–organization relations (Doddington et al., 2004), protein– protein interactions (PPI), and disease–gene as- sociations (DGA) (Chun et al., 2006). Among the possible RE tasks, we chose the PPI extrac- tion problem. PPI extraction is a major RE task; around 10 corpora have been published for train- ing and evaluation of PPI extraction systems. Recently, machine-learning methods, boosted by NLP techniques, have proved to be effec- tive for RE. These methods are usually intended to highlight or select the relation-related regions in parsed sentences using feature vectors or ker- nels. The shortest paths between a pair of enti- ties (Bunescu and Mooney, 2005) or pair-enclosed trees (Zhang et al., 2006) are widely used as focus regions. These regions are useful, but they can in- clude unnecessary sub-paths such as appositions, which cause noisy features. In this paper, we propose a method to remove information that is deemed unnecessary for RE. Instead of selecting the whole region between a target pair, the target sentence is simplified into simpler, pair-related, sentences using general, task-independent, rules. By addressing particu- larly the target entities, the rules do not affect im- portant relation-related expressions between the target entities. We show how rules of two groups can be easily defined using the analytical capabil- ity of a deep parser with specific examination of the target entities. Rules of the first group can re- place a sentence with a simpler sentence, still in- cluding the two target entities. The other group of rules can replace a large region (phrase) represent- ing one target entity, with just a simple mention of that target entity. With only a dozen simple rules, we show that we …

Content truncated to 500 words