A Comparison of Loopy Belief Propagation and Dual Decomposition for Integrated CCG Supertagging and Parsing

Michael Auli, Adam Lopez

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Via an oracle experiment, we show that the upper bound on accuracy of a CCG parser is significantly lowered when its search space is pruned using a supertagger, though the supertagger also prunes many bad parses. Inspired by this analysis, we design a single model with both supertagging and parsing features, rather than separating them into distinct models chained together in a pipeline. To overcome the resulting increase in complexity, we experiment with both belief propagation and dual decomposition approaches to inference, the first empirical comparison of these algorithms that we are aware of on a structured natural language processing problem. On CCGbank we achieve a labelled dependency F-measure of 88.8% on gold POS tags, and 86.7% on automatic part-of-speech tags, the best reported results for this task.
Original languageEnglish
Title of host publicationProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies
Place of PublicationPortland, Oregon, USA
PublisherAssociation for Computational Linguistics
Pages470-480
Number of pages11
Publication statusPublished - 1 Jun 2011

Fingerprint

Dive into the research topics of 'A Comparison of Loopy Belief Propagation and Dual Decomposition for Integrated CCG Supertagging and Parsing'. Together they form a unique fingerprint.

Cite this