Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation

Gumwon Hong; Seung Wook Lee; Hae Chang Rim

doi:10.3115/1667583.1667655

Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation

Gumwon Hong, Seung Wook Lee, Hae Chang Rim

* Honorary professors

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

16 Citations (Scopus)

Abstract

Often, Statistical Machine Translation (SMT) between English and Korean suffers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessary function words, or by reordering source sentences. However, the removal of function words can cause a serious loss in information. In this paper, we present a possible method of bridging the morpho-syntactic gap for English-Korean SMT. In particular, the proposed method tries to transform a source sentence by inserting pseudo words, and by reordering the sentence in such a way that both sentences have a similar length and word order. The proposed method achieves 2.4 increase in BLEU score over baseline phrase-based system.

Original language	English
Title of host publication	ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.
Publisher	Association for Computational Linguistics (ACL)
Pages	233-236
Number of pages	4
ISBN (Print)	9781617382581
DOIs	https://doi.org/10.3115/1667583.1667655
Publication status	Published - 2009
Event	Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 - Suntec, Singapore Duration: 2009 Aug 2 → 2009 Aug 7

Publication series

Name	ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.

Other

Other	Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009
Country/Territory	Singapore
City	Suntec
Period	09/8/2 → 09/8/7

Bibliographical note

Funding Information:
This work was supported by Microsoft Research Asia. Any opinions, findings, and conclusions or recommendations expressed above are those of the authors and do not necessarily reflect the views of the sponsor.

ASJC Scopus subject areas

Language and Linguistics
Linguistics and Language
Artificial Intelligence
Software

Access to Document

10.3115/1667583.1667655

Cite this

Hong, G., Lee, S. W., & Rim, H. C. (2009). Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf. (pp. 233-236). (ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1667583.1667655

Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation. / Hong, Gumwon; Lee, Seung Wook; Rim, Hae Chang.
ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. Association for Computational Linguistics (ACL), 2009. p. 233-236 (ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hong, G, Lee, SW & Rim, HC 2009, Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation. in ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf., Association for Computational Linguistics (ACL), pp. 233-236, Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009, Suntec, Singapore, 09/8/2. https://doi.org/10.3115/1667583.1667655

Hong G, Lee SW, Rim HC. Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation. In ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. Association for Computational Linguistics (ACL). 2009. p. 233-236. (ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.). doi: 10.3115/1667583.1667655

Hong, Gumwon ; Lee, Seung Wook ; Rim, Hae Chang. / Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation. ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.. Association for Computational Linguistics (ACL), 2009. pp. 233-236 (ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.).

@inproceedings{a1df2bf5764b494fb64596c2282059ab,

title = "Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation",

abstract = "Often, Statistical Machine Translation (SMT) between English and Korean suffers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessary function words, or by reordering source sentences. However, the removal of function words can cause a serious loss in information. In this paper, we present a possible method of bridging the morpho-syntactic gap for English-Korean SMT. In particular, the proposed method tries to transform a source sentence by inserting pseudo words, and by reordering the sentence in such a way that both sentences have a similar length and word order. The proposed method achieves 2.4 increase in BLEU score over baseline phrase-based system.",

author = "Gumwon Hong and Lee, {Seung Wook} and Rim, {Hae Chang}",

note = "Funding Information: This work was supported by Microsoft Research Asia. Any opinions, findings, and conclusions or recommendations expressed above are those of the authors and do not necessarily reflect the views of the sponsor.; Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009 ; Conference date: 02-08-2009 Through 07-08-2009",

year = "2009",

doi = "10.3115/1667583.1667655",

language = "English",

isbn = "9781617382581",

series = "ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.",

publisher = "Association for Computational Linguistics (ACL)",

pages = "233--236",

booktitle = "ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.",

}

TY - GEN

T1 - Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation

AU - Hong, Gumwon

AU - Lee, Seung Wook

AU - Rim, Hae Chang

N1 - Funding Information: This work was supported by Microsoft Research Asia. Any opinions, findings, and conclusions or recommendations expressed above are those of the authors and do not necessarily reflect the views of the sponsor.

PY - 2009

Y1 - 2009

N2 - Often, Statistical Machine Translation (SMT) between English and Korean suffers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessary function words, or by reordering source sentences. However, the removal of function words can cause a serious loss in information. In this paper, we present a possible method of bridging the morpho-syntactic gap for English-Korean SMT. In particular, the proposed method tries to transform a source sentence by inserting pseudo words, and by reordering the sentence in such a way that both sentences have a similar length and word order. The proposed method achieves 2.4 increase in BLEU score over baseline phrase-based system.

AB - Often, Statistical Machine Translation (SMT) between English and Korean suffers from null alignment. Previous studies have attempted to resolve this problem by removing unnecessary function words, or by reordering source sentences. However, the removal of function words can cause a serious loss in information. In this paper, we present a possible method of bridging the morpho-syntactic gap for English-Korean SMT. In particular, the proposed method tries to transform a source sentence by inserting pseudo words, and by reordering the sentence in such a way that both sentences have a similar length and word order. The proposed method achieves 2.4 increase in BLEU score over baseline phrase-based system.

UR - http://www.scopus.com/inward/record.url?scp=80053280905&partnerID=8YFLogxK

U2 - 10.3115/1667583.1667655

DO - 10.3115/1667583.1667655

M3 - Conference contribution

AN - SCOPUS:80053280905

SN - 9781617382581

T3 - ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.

SP - 233

EP - 236

BT - ACL-IJCNLP 2009 - Joint Conf. of the 47th Annual Meeting of the Association for Computational Linguistics and 4th Int. Joint Conf. on Natural Language Processing of the AFNLP, Proceedings of the Conf.

PB - Association for Computational Linguistics (ACL)

T2 - Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing of the AFNLP, ACL-IJCNLP 2009

Y2 - 2 August 2009 through 7 August 2009

ER -

Bridging morpho-syntactic gap between source and target sentences for English-Korean Statistical Machine Translation

Abstract

Publication series

Other

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this