Paper: Relation Extraction with Relation Topics

ACL ID D11-1132
Title Relation Extraction with Relation Topics
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2011
Authors

This paper describes a novel approach to the semantic relation detection problem. Instead of relying only on the training instances for a new relation, we leverage the knowledge learned from previously trained relation detec- tors. Speci cally, we detect a new semantic relation by projecting the new relation’s train- ing instances onto a lower dimension topic space constructed from existing relation de- tectors through a three step process. First, we construct a large relation repository of more than 7,000 relations from Wikipedia. Second, we construct a set of non-redundant relation topics de ned at multiple scales from the re- lation repository to characterize the existing relations. Similar to the topics de ned over words, each relation topic is an interpretable multinomial distributi...