Paper: Joint Unsupervised Coreference Resolution with Markov Logic

ACL ID D08-1068
Title Joint Unsupervised Coreference Resolution with Markov Logic
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2008

Machine learning approaches to coreference resolution are typically supervised, and re- quire expensive labeled data. Some unsuper- vised approaches have been proposed (e.g., Haghighi and Klein (2007)), but they are less accurate. In this paper, we present the first un- supervised approach that is competitive with supervised ones. This is made possible by performing joint inference across mentions, in contrast to the pairwise classification typ- ically used in supervised methods, and by us- ingMarkovlogicasarepresentationlanguage, which enables us to easily express relations like apposition and predicate nominals. On MUC and ACE datasets, our model outper- forms Haghigi and Klein’s one using only a fractionofthetrainingdata, andoftenmatches or exceeds the accuracy of state-of-the-art su-...