Domain adaptation for coreference resolution: An adaptive ensemble approach

Publication Type:
Conference Proceeding
Citation:
EMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference, 2012, pp. 744 - 753
Issue Date:
2012-12-01
Metrics:
Full metadata record
Files in This Item:
Filename Description Size
domain.pdfPublished version658.02 kB
Adobe PDF
We propose an adaptive ensemble method to adapt coreference resolution across domains. This method has three features: (1) it can optimize for any user-specified objective measure; (2) it can make document-specific prediction rather than rely on a fixed base model or a fixed set of base models; (3) it can automatically adjust the active ensemble members during prediction. With simplification, this method can be used in the traditional within-domain case, while still retaining the above features. To the best of our knowledge, this work is the first to both (i) develop a domain adaptation algorithm for the coreference resolution problem and (ii) have the above features as an ensemble method. Empirically, we show the benefits of (i) on the six domains of the ACE 2005 data set in domain adaptation setting, and of (ii) on both the MUC-6 and the ACE 2005 data sets in within-domain setting. © 2012 Association for Computational Linguistics.
Please use this identifier to cite or link to this item: