%0 Journal Article %1 yates2009 %A Yates, Alexander %A Etzioni, Oren %C USA %D 2009 %I AI Access Foundation %J J. Artif. Int. Res. %K 2009 extension extraction relation resolver textrunner unsupervised yates %N 1 %P 255--296 %T Unsupervised Methods for Determining Object and Relation Synonyms on the Web %U http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.178.3420&rep=rep1&type=pdf %V 34 %X The task of identifying synonymous relations and objects, or synonym resolution, is critical for high-quality information extraction. This paper investigates synonym resolution in the context of unsupervised information extraction, where neither hand-tagged training examples nor domain knowledge is available. The paper presents a scalable, fully-implemented system 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. On a set of two million assertions extracted from the Web, RESOLVER resolves objects with 78% precision and 68% recall, and resolves relations with 90% precision and 35% recall. Several variations of RESOLVER's probabilistic model are explored, and experiments demonstrate that under appropriate conditions these variations can improve F1 by 5%. An extension to the basic RESOLVER system allows it to handle polysemous names with 97% precision and 95% recall on a data set from the TREC corpus.

@article{yates2009, abstract = {The task of identifying synonymous relations and objects, or synonym resolution, is critical for high-quality information extraction. This paper investigates synonym resolution in the context of unsupervised information extraction, where neither hand-tagged training examples nor domain knowledge is available. The paper presents a scalable, fully-implemented system 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. On a set of two million assertions extracted from the Web, RESOLVER resolves objects with 78% precision and 68% recall, and resolves relations with 90% precision and 35% recall. Several variations of RESOLVER's probabilistic model are explored, and experiments demonstrate that under appropriate conditions these variations can improve F1 by 5%. An extension to the basic RESOLVER system allows it to handle polysemous names with 97% precision and 95% recall on a data set from the TREC corpus.}, acmid = {1622724}, added-at = {2014-01-05T16:40:56.000+0100}, address = {USA}, author = {Yates, Alexander and Etzioni, Oren}, biburl = {https://www.bibsonomy.org/bibtex/21bd33c34f6f19468897b9688ce792df9/jil}, interhash = {37c084ce21a33c31b5a62530145c5a08}, intrahash = {1bd33c34f6f19468897b9688ce792df9}, issn = {1076-9757}, issue_date = {January 2009}, journal = {J. Artif. Int. Res.}, keywords = {2009 extension extraction relation resolver textrunner unsupervised yates}, month = mar, number = 1, numpages = {42}, pages = {255--296}, publisher = {AI Access Foundation}, timestamp = {2014-01-05T16:43:21.000+0100}, title = {Unsupervised Methods for Determining Object and Relation Synonyms on the Web}, url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.178.3420&rep=rep1&type=pdf}, volume = 34, year = 2009 }