Improved parsing and POS tagging using inter-sentence consistency constraints

Alexander M. Rush, Roi Reichart, Michael Collins, Amir Globerson

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

State-of-the-art statistical parsers and POS taggers perform very well when trained with large amounts of in-domain data. When training data is out-of-domain or limited, accuracy degrades. In this paper, we aim to compensate for the lack of available training data by exploiting similarities between test set sentences. We show how to augment sentence-level models for parsing and POS tagging with inter-sentence consistency constraints. To deal with the resulting global objective, we present an efficient and exact dual decomposition decoding algorithm. In experiments, we add consistency constraints to the MST parser and the Stanford part-of-speech tagger and demonstrate significant error reduction in the domain adaptation and the lightly supervised settings across five languages.

Original languageEnglish
Title of host publicationEMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference
Pages1434-1444
Number of pages11
StatePublished - 2012
Externally publishedYes
Event2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012 - Jeju Island, Korea, Republic of
Duration: 12 Jul 201214 Jul 2012

Publication series

NameEMNLP-CoNLL 2012 - 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, Proceedings of the Conference

Conference

Conference2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2012
Country/TerritoryKorea, Republic of
CityJeju Island
Period12/07/1214/07/12

Fingerprint

Dive into the research topics of 'Improved parsing and POS tagging using inter-sentence consistency constraints'. Together they form a unique fingerprint.

Cite this