Joint Unsupervised Coreference Resolution with Markov Logic
Hoifung Poon and Pedro Domingos
Abstract:
Machine learning approaches to coreference
resolution are typically supervised, and require
expensive labeled data. Some unsupervised
approaches have been proposed (e.g.,
Haghighi and Klein (2007)), but they are less
accurate. In this paper, we present the first unsupervised
approach that is competitive with
supervised ones. This is made possible by
performing joint inference across mentions,
in contrast to the pairwise classification typically
used in supervised methods, and by using
Markov logic as a representation language,
which enables us to easily express relations
like apposition and predicate nominals. On
MUC and ACE datasets, our model outperforms
Haghigi and Klein's one using only a
fraction of the training data, and often matches
or exceeds the accuracy of state-of-the-art supervised
models.
Download:
Paper (PDF)
MLNs used:
Joint Unsupervised Coreference Resolution
Datasets used:
(Note: Due to license restriction, we are not able to release these datasets. They can be acquired from the Linguistic Data Consortium)
MUC-6
ACE 2004 Training Corpus
ACE-2 (Phrase II)