Paper: Unsupervised Resolution of Objects and Relations on the Web

ACL ID N07-1016
Title Unsupervised Resolution of Objects and Relations on the Web
Venue Human Language Technologies
Session Main Conference
Year 2007
Authors

The task of identifying synonymous re- lations and objects, or Synonym Resolu- tion (SR), is critical for high-quality infor- mation extraction. The bulk of previous SR work assumed strong domain knowl- edge or hand-tagged training examples. This paper investigates SR in the con- text of unsupervised information extrac- tion, where neither is available. The pa- per presents a scalable, fully-implemented system for SR that runs in O(KN log N) time in the number of extractions N and the maximum number of synonyms per word, K. The system, called RESOLVER, introduces a probabilistic relational model for predicting whether two strings are co-referential based on the similarity of the assertions containing them. Given two million assertions extracted from the Web, RESOLVER resolves objects with ...