A post-processing approach to statistical word alignment reflecting alignment tendency between part-of-speeches

Jae Hee Lee; Seung Wook Lee; Gumwon Hong; Young Sook Hwang; Sang Bum Kim; Hae Chang Rim

A post-processing approach to statistical word alignment reflecting alignment tendency between part-of-speeches

Jae Hee Lee, Seung Wook Lee, Gumwon Hong, Young Sook Hwang, Sang Bum Kim, Hae Chang Rim

Research output: Contribution to conference › Paper › peer-review

Abstract

Statistical word alignment often suffers from data sparseness. Part-of-speeches are often incorporated in NLP tasks to reduce data sparseness. In this paper, we attempt to mitigate such problem by reflecting alignment tendency between part-of-speeches to statistical word alignment. Because our approach does not rely on any language-dependent knowledge, it is very simple and purely statistic to be applied to any language pairs. End-to-end evaluation shows that the proposed method can improve not only the quality of statistical word alignment but the performance of statistical machine translation.

Original language	English
Pages	623-629
Number of pages	7
Publication status	Published - 2010
Event	23rd International Conference on Computational Linguistics, Coling 2010 - Beijing, China Duration: 2010 Aug 23 → 2010 Aug 27

Other

Other	23rd International Conference on Computational Linguistics, Coling 2010
Country/Territory	China
City	Beijing
Period	10/8/23 → 10/8/27

ASJC Scopus subject areas

Language and Linguistics
Computational Theory and Mathematics
Linguistics and Language

Cite this

@conference{c101a3345dd640549eb6be6f8ba31176,

title = "A post-processing approach to statistical word alignment reflecting alignment tendency between part-of-speeches",

abstract = "Statistical word alignment often suffers from data sparseness. Part-of-speeches are often incorporated in NLP tasks to reduce data sparseness. In this paper, we attempt to mitigate such problem by reflecting alignment tendency between part-of-speeches to statistical word alignment. Because our approach does not rely on any language-dependent knowledge, it is very simple and purely statistic to be applied to any language pairs. End-to-end evaluation shows that the proposed method can improve not only the quality of statistical word alignment but the performance of statistical machine translation.",

author = "Lee, {Jae Hee} and Lee, {Seung Wook} and Gumwon Hong and Hwang, {Young Sook} and Kim, {Sang Bum} and Rim, {Hae Chang}",

year = "2010",

language = "English",

pages = "623--629",

note = "23rd International Conference on Computational Linguistics, Coling 2010 ; Conference date: 23-08-2010 Through 27-08-2010",

}

TY - CONF

T1 - A post-processing approach to statistical word alignment reflecting alignment tendency between part-of-speeches

AU - Lee, Jae Hee

AU - Lee, Seung Wook

AU - Hong, Gumwon

AU - Hwang, Young Sook

AU - Kim, Sang Bum

AU - Rim, Hae Chang

PY - 2010

Y1 - 2010

N2 - Statistical word alignment often suffers from data sparseness. Part-of-speeches are often incorporated in NLP tasks to reduce data sparseness. In this paper, we attempt to mitigate such problem by reflecting alignment tendency between part-of-speeches to statistical word alignment. Because our approach does not rely on any language-dependent knowledge, it is very simple and purely statistic to be applied to any language pairs. End-to-end evaluation shows that the proposed method can improve not only the quality of statistical word alignment but the performance of statistical machine translation.

AB - Statistical word alignment often suffers from data sparseness. Part-of-speeches are often incorporated in NLP tasks to reduce data sparseness. In this paper, we attempt to mitigate such problem by reflecting alignment tendency between part-of-speeches to statistical word alignment. Because our approach does not rely on any language-dependent knowledge, it is very simple and purely statistic to be applied to any language pairs. End-to-end evaluation shows that the proposed method can improve not only the quality of statistical word alignment but the performance of statistical machine translation.

UR - http://www.scopus.com/inward/record.url?scp=80053434256&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053434256&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:80053434256

SP - 623

EP - 629

T2 - 23rd International Conference on Computational Linguistics, Coling 2010

Y2 - 23 August 2010 through 27 August 2010

ER -

A post-processing approach to statistical word alignment reflecting alignment tendency between part-of-speeches

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this