Simpler unsupervised POS tagging with bilingual projections

Long Duong, Paul Cook, Steven Bird, Pavel Pecina

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

Abstract

We present an unsupervised approach to part-of-speech tagging based on projections of tags in a word-aligned bilingual parallel corpus. In contrast to the existing state-of-The-art approach of Das and Petrov, we have developed a substantially simpler method by automatically identifying "good" training sentences from the parallel corpus and applying self-training. In experimental results on eight languages, our method achieves state-of-The-art results.

Original languageEnglish
Title of host publicationProceedings of the 51st Annual Meeting of the Association for Computational Linguistics
EditorsPascale Fung, Massimo Poesio
Place of PublicationSofia, Bulgaria
PublisherAssociation for Computational Linguistics (ACL)
Pages634-639
Number of pages6
Volume2
ISBN (Print)9781937284510
Publication statusPublished - 2013
Externally publishedYes
Event51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 - Sofia, Bulgaria
Duration: 4 Aug 20139 Aug 2013

Conference

Conference51st Annual Meeting of the Association for Computational Linguistics, ACL 2013
CountryBulgaria
CitySofia
Period4/08/139/08/13

Fingerprint

projection
language
Parallel Corpora
Tagging
Part-of-speech Tagging
Language
Tag

Cite this

Duong, L., Cook, P., Bird, S., & Pecina, P. (2013). Simpler unsupervised POS tagging with bilingual projections. In P. Fung, & M. Poesio (Eds.), Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Vol. 2, pp. 634-639). Sofia, Bulgaria: Association for Computational Linguistics (ACL).
Duong, Long ; Cook, Paul ; Bird, Steven ; Pecina, Pavel. / Simpler unsupervised POS tagging with bilingual projections. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. editor / Pascale Fung ; Massimo Poesio. Vol. 2 Sofia, Bulgaria : Association for Computational Linguistics (ACL), 2013. pp. 634-639
@inproceedings{e0ada5ea6efd4cd282f019155e66de24,
title = "Simpler unsupervised POS tagging with bilingual projections",
abstract = "We present an unsupervised approach to part-of-speech tagging based on projections of tags in a word-aligned bilingual parallel corpus. In contrast to the existing state-of-The-art approach of Das and Petrov, we have developed a substantially simpler method by automatically identifying {"}good{"} training sentences from the parallel corpus and applying self-training. In experimental results on eight languages, our method achieves state-of-The-art results.",
author = "Long Duong and Paul Cook and Steven Bird and Pavel Pecina",
year = "2013",
language = "English",
isbn = "9781937284510",
volume = "2",
pages = "634--639",
editor = "Pascale Fung and Massimo Poesio",
booktitle = "Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics",
publisher = "Association for Computational Linguistics (ACL)",

}

Duong, L, Cook, P, Bird, S & Pecina, P 2013, Simpler unsupervised POS tagging with bilingual projections. in P Fung & M Poesio (eds), Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. vol. 2, Association for Computational Linguistics (ACL), Sofia, Bulgaria, pp. 634-639, 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013, Sofia, Bulgaria, 4/08/13.

Simpler unsupervised POS tagging with bilingual projections. / Duong, Long; Cook, Paul; Bird, Steven; Pecina, Pavel.

Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. ed. / Pascale Fung; Massimo Poesio. Vol. 2 Sofia, Bulgaria : Association for Computational Linguistics (ACL), 2013. p. 634-639.

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

TY - GEN

T1 - Simpler unsupervised POS tagging with bilingual projections

AU - Duong, Long

AU - Cook, Paul

AU - Bird, Steven

AU - Pecina, Pavel

PY - 2013

Y1 - 2013

N2 - We present an unsupervised approach to part-of-speech tagging based on projections of tags in a word-aligned bilingual parallel corpus. In contrast to the existing state-of-The-art approach of Das and Petrov, we have developed a substantially simpler method by automatically identifying "good" training sentences from the parallel corpus and applying self-training. In experimental results on eight languages, our method achieves state-of-The-art results.

AB - We present an unsupervised approach to part-of-speech tagging based on projections of tags in a word-aligned bilingual parallel corpus. In contrast to the existing state-of-The-art approach of Das and Petrov, we have developed a substantially simpler method by automatically identifying "good" training sentences from the parallel corpus and applying self-training. In experimental results on eight languages, our method achieves state-of-The-art results.

UR - http://www.scopus.com/inward/record.url?scp=84907304171&partnerID=8YFLogxK

UR - https://aclanthology.info/volumes/proceedings-of-the-51st-annual-meeting-of-the-association-for-computational-linguistics-volume-2-short-papers

M3 - Conference Paper published in Proceedings

SN - 9781937284510

VL - 2

SP - 634

EP - 639

BT - Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics

A2 - Fung, Pascale

A2 - Poesio, Massimo

PB - Association for Computational Linguistics (ACL)

CY - Sofia, Bulgaria

ER -

Duong L, Cook P, Bird S, Pecina P. Simpler unsupervised POS tagging with bilingual projections. In Fung P, Poesio M, editors, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics. Vol. 2. Sofia, Bulgaria: Association for Computational Linguistics (ACL). 2013. p. 634-639