Predicate-argument reordering based on learning to rank for english-korean machine translation

Joo Young Lee, Gumwon Hong, Hae-Chang Rim, Young In Song, Young Sook Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose a method of learning predicateargument structure reordering, and present its effect on machine translation. The method takes two steps; first, it extracts generalized predicate-argument structure reordering rules using a source sentence parse tree from a parallel corpus. Second, it trains a model based on learning to rank framework to select the most relevant reordering rule based on source language context features. The learned model is used to restructure a source sentence in order to have similar word order with a target sentence. In our experiments on English-to-Korean machine translation, the proposed method achieves significant improvements in BLEU score, from 19.68 to 21.84.

Original languageEnglish
Title of host publicationProceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011
DOIs
Publication statusPublished - 2011 May 20
Event5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011 - Seoul, Korea, Republic of
Duration: 2011 Feb 212011 Feb 23

Other

Other5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011
CountryKorea, Republic of
CitySeoul
Period11/2/2111/2/23

Fingerprint

Experiments

Keywords

  • Learning to rank
  • Machine translation
  • Predicate-argument
  • Preprocessing
  • Reordering

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Lee, J. Y., Hong, G., Rim, H-C., Song, Y. I., & Hwang, Y. S. (2011). Predicate-argument reordering based on learning to rank for english-korean machine translation. In Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011 [2] https://doi.org/10.1145/1968613.1968616

Predicate-argument reordering based on learning to rank for english-korean machine translation. / Lee, Joo Young; Hong, Gumwon; Rim, Hae-Chang; Song, Young In; Hwang, Young Sook.

Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011. 2011. 2.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lee, JY, Hong, G, Rim, H-C, Song, YI & Hwang, YS 2011, Predicate-argument reordering based on learning to rank for english-korean machine translation. in Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011., 2, 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011, Seoul, Korea, Republic of, 11/2/21. https://doi.org/10.1145/1968613.1968616
Lee JY, Hong G, Rim H-C, Song YI, Hwang YS. Predicate-argument reordering based on learning to rank for english-korean machine translation. In Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011. 2011. 2 https://doi.org/10.1145/1968613.1968616
Lee, Joo Young ; Hong, Gumwon ; Rim, Hae-Chang ; Song, Young In ; Hwang, Young Sook. / Predicate-argument reordering based on learning to rank for english-korean machine translation. Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011. 2011.
@inproceedings{075586f20d31424e8ed39fec0af02bd1,
title = "Predicate-argument reordering based on learning to rank for english-korean machine translation",
abstract = "In this paper, we propose a method of learning predicateargument structure reordering, and present its effect on machine translation. The method takes two steps; first, it extracts generalized predicate-argument structure reordering rules using a source sentence parse tree from a parallel corpus. Second, it trains a model based on learning to rank framework to select the most relevant reordering rule based on source language context features. The learned model is used to restructure a source sentence in order to have similar word order with a target sentence. In our experiments on English-to-Korean machine translation, the proposed method achieves significant improvements in BLEU score, from 19.68 to 21.84.",
keywords = "Learning to rank, Machine translation, Predicate-argument, Preprocessing, Reordering",
author = "Lee, {Joo Young} and Gumwon Hong and Hae-Chang Rim and Song, {Young In} and Hwang, {Young Sook}",
year = "2011",
month = "5",
day = "20",
doi = "10.1145/1968613.1968616",
language = "English",
isbn = "9781450305716",
booktitle = "Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011",

}

TY - GEN

T1 - Predicate-argument reordering based on learning to rank for english-korean machine translation

AU - Lee, Joo Young

AU - Hong, Gumwon

AU - Rim, Hae-Chang

AU - Song, Young In

AU - Hwang, Young Sook

PY - 2011/5/20

Y1 - 2011/5/20

N2 - In this paper, we propose a method of learning predicateargument structure reordering, and present its effect on machine translation. The method takes two steps; first, it extracts generalized predicate-argument structure reordering rules using a source sentence parse tree from a parallel corpus. Second, it trains a model based on learning to rank framework to select the most relevant reordering rule based on source language context features. The learned model is used to restructure a source sentence in order to have similar word order with a target sentence. In our experiments on English-to-Korean machine translation, the proposed method achieves significant improvements in BLEU score, from 19.68 to 21.84.

AB - In this paper, we propose a method of learning predicateargument structure reordering, and present its effect on machine translation. The method takes two steps; first, it extracts generalized predicate-argument structure reordering rules using a source sentence parse tree from a parallel corpus. Second, it trains a model based on learning to rank framework to select the most relevant reordering rule based on source language context features. The learned model is used to restructure a source sentence in order to have similar word order with a target sentence. In our experiments on English-to-Korean machine translation, the proposed method achieves significant improvements in BLEU score, from 19.68 to 21.84.

KW - Learning to rank

KW - Machine translation

KW - Predicate-argument

KW - Preprocessing

KW - Reordering

UR - http://www.scopus.com/inward/record.url?scp=79956036793&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79956036793&partnerID=8YFLogxK

U2 - 10.1145/1968613.1968616

DO - 10.1145/1968613.1968616

M3 - Conference contribution

SN - 9781450305716

BT - Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 2011

ER -