Simpler unsupervised POS tagging with bilingual projections

Long Duong; Paul Cook; Steven Bird; Pavel Pecina

Simpler unsupervised POS tagging with bilingual projections

Long Duong, Paul Cook, Steven Bird, Pavel Pecina

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-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 language	English
Title of host publication	Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics
Editors	Pascale Fung, Massimo Poesio
Place of Publication	Sofia, Bulgaria
Publisher	Association for Computational Linguistics (ACL)
Pages	634-639
Number of pages	6
Volume	2
ISBN (Print)	9781937284510
Publication status	Published - 2013
Externally published	Yes
Event	51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 - Sofia, Bulgaria Duration: 4 Aug 2013 → 9 Aug 2013

Conference

Conference	51st Annual Meeting of the Association for Computational Linguistics, ACL 2013
Country/Territory	Bulgaria
City	Sofia
Period	4/08/13 → 9/08/13

Cite this

@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)",

note = "51st Annual Meeting of the Association for Computational Linguistics, ACL 2013 ; Conference date: 04-08-2013 Through 09-08-2013",

}

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 et al.

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 proceeding › Conference Paper published in Proceedings › peer-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

AN - SCOPUS:84907304171

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

T2 - 51st Annual Meeting of the Association for Computational Linguistics, ACL 2013

Y2 - 4 August 2013 through 9 August 2013

ER -

Simpler unsupervised POS tagging with bilingual projections

Abstract

Conference

Other files and links

Fingerprint

Cite this