We present a Bayesian formulation for weakly-supervised learning of a Combinatory Categorial Grammar (CCG) supertagger with an HMM. We assume supervision in the form of a tag dictionary, and our prior encourages the use of cross-linguistically common category structures as well as transitions between tags that can combine locally according to CCG's combinators. Our prior is theoretically appealing since it is motivated by language-independent, universal properties of the CCG formalism. Empirically, we show that it yields substantial improvements over previous work that used similar biases to initialize an EM-based learner. Additional gains are obtained by further shaping the prior with corpus-specific information that is extracted automatically from raw text and a tag dictionary.

PDF

In Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL-2014), pp. 141--150, Baltimore, MD, June 2014.

@inproceedings{garrette:conll14, title={Weakly-Supervised Bayesian Learning of a CCG Supertagger}, author={Dan Garrette and Chris Dyer and Jason Baldridge and Noah A. Smith}, booktitle={Proceedings of the Eighteenth Conference on Computational Natural Language Learning (CoNLL-2014)}, month={June}, address={Baltimore, MD}, pages={141--150}, url="http://www.cs.utexas.edu/users/ai-labpub-view.php?PubID=127470", year={2014} }

Slides (PDF) Poster