Paper: Employing Word Representations and Regularization for Domain Adaptation of Relation Extraction

ACL ID P14-2012
Title Employing Word Representations and Regularization for Domain Adaptation of Relation Extraction
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

Relation extraction suffers from a perfor- mance loss when a model is applied to out-of-domain data. This has fostered the development of domain adaptation tech- niques for relation extraction. This paper evaluates word embeddings and clustering on adapting feature-based relation extrac- tion systems. We systematically explore various ways to apply word embeddings and show the best adaptation improvement by combining word cluster and word em- bedding information. Finally, we demon- strate the effectiveness of regularization for the adaptability of relation extractors.