Paper: ARE: Instance Splitting Strategies For Dependency Relation-Based Information Extraction

ACL ID P06-2074
Title ARE: Instance Splitting Strategies For Dependency Relation-Based Information Extraction
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006
Authors

Information Extraction (IE) is a fundamen- tal technology for NLP. Previous methods for IE were relying on co-occurrence rela- tions, soft patterns and properties of the target (for example, syntactic role), which result in problems of handling paraphrasing and alignment of instances. Our system ARE (Anchor and Relation) is based on the dependency relation model and tackles these problems by unifying entities accord- ing to their dependency relations, which we found to provide more invariant relations between entities in many cases. In order to exploit the complexity and characteristics of relation paths, we further classify the re- lation paths into the categories of ‘easy’, ‘average’ and ‘hard’, and utilize different extraction strategies based on the character- istics of tho...