Semi-Supervised Learning of Sequence Models with the Method of Moments

Zita Marinho Marinho, Andre F. T. Martin, Shay Cohen, Noah A. Smith

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

Abstract

We propose a fast and scalable method for semi-supervised learning of sequence models, based on anchor words and moment matching. Our method can handle hidden Markov models with feature-based log-linear emissions. Unlike other semi-supervised methods, no decoding passes are necessary on the unlabeled data and no graph needs to be constructed— only one pass is necessary to collect moment statistics. The model parameters are estimated by solving a small quadratic program for each feature. Experiments on part-of-speech (POS) tagging for Twitter and for a low-resource language (Malagasy) show that our method can learn from very few annotated sentences.
Original languageEnglish
Title of host publicationProceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
Place of PublicationAustin, Texas
PublisherAssociation for Computational Linguistics (ACL)
Pages287-296
Number of pages10
ISBN (Electronic)978-1-945626-25-8
DOIs
Publication statusPublished - 5 Nov 2016
Event2016 Conference on Empirical Methods in Natural Language Processing - Austin, United States
Duration: 1 Nov 20165 Nov 2016
https://www.aclweb.org/mirror/emnlp2016/

Conference

Conference2016 Conference on Empirical Methods in Natural Language Processing
Abbreviated titleEMNLP 2016
Country/TerritoryUnited States
CityAustin
Period1/11/165/11/16
Internet address

Fingerprint

Dive into the research topics of 'Semi-Supervised Learning of Sequence Models with the Method of Moments'. Together they form a unique fingerprint.

Cite this