Simple Semi-Supervised Learning for Prepositional Phrase Attachment

Gregory F. Coppola, Alexandra Birch, Tejaswini Deoskar, Mark Steedman

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

Abstract / Description of output

Prepositional phrase attachment is an important subproblem of parsing, performance on which suffers from limited availability of labelled data. We present a semi-supervised approach. We show that a discriminative lexical model trained from labelled data, and a generative lexical model learned via Expectation Maximization from unlabelled data can be combined in a product model to yield a PP-attachment model which is better than either is alone, and which outperforms the modern parser of Petrov and Klein (2007) by a significant margin. We show that, when learning from unlabelled data, it can be beneficial to model the generation of modifiers of a head collectively, rather than individually. Finally, we suggest that our pair of models will be interesting to combine using new techniques for discriminatively constraining EM.
Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Parsing Technologies, IWPT 2011, October 5-7, 2011, Dublin City University, Dubin, Ireland
PublisherAssociation for Computational Linguistics
Number of pages11
Publication statusPublished - 2011


Dive into the research topics of 'Simple Semi-Supervised Learning for Prepositional Phrase Attachment'. Together they form a unique fingerprint.

Cite this