Utilizing global syntactic tree features for phrase reordering

Yeon Soo Lee, Hyoung Gyu Lee, Hae-Chang Rim, Young Sook Hwang

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In phrase-based statistical machine translation, long distance reordering problem is one of the most challenging issues when translating syntactically distant language pairs. In this paper, we propose a novel reordering model to solve this problem. In our model, reordering is affected by the overall structures of sentences such as listings, reduplications, and modifications as well as the relationships of adjacent phrases. To this end, we reflect global syntactic contexts including the parts that are not yet translated during the decoding process.

Original languageEnglish
Pages (from-to)1694-1698
Number of pages5
JournalIEICE Transactions on Information and Systems
VolumeE97-D
Issue number6
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Syntactics
Decoding

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence

Cite this

Utilizing global syntactic tree features for phrase reordering. / Lee, Yeon Soo; Lee, Hyoung Gyu; Rim, Hae-Chang; Hwang, Young Sook.

In: IEICE Transactions on Information and Systems, Vol. E97-D, No. 6, 01.01.2014, p. 1694-1698.

Research output: Contribution to journalArticle

Lee, Yeon Soo ; Lee, Hyoung Gyu ; Rim, Hae-Chang ; Hwang, Young Sook. / Utilizing global syntactic tree features for phrase reordering. In: IEICE Transactions on Information and Systems. 2014 ; Vol. E97-D, No. 6. pp. 1694-1698.
@article{25652a117f9d41968e4987f222e62219,
title = "Utilizing global syntactic tree features for phrase reordering",
abstract = "In phrase-based statistical machine translation, long distance reordering problem is one of the most challenging issues when translating syntactically distant language pairs. In this paper, we propose a novel reordering model to solve this problem. In our model, reordering is affected by the overall structures of sentences such as listings, reduplications, and modifications as well as the relationships of adjacent phrases. To this end, we reflect global syntactic contexts including the parts that are not yet translated during the decoding process.",
keywords = "Global syntactic tree features, Phrase reordering model, Phrase-based statistical machine translation",
author = "Lee, {Yeon Soo} and Lee, {Hyoung Gyu} and Hae-Chang Rim and Hwang, {Young Sook}",
year = "2014",
month = "1",
day = "1",
doi = "10.1587/transinf.E97.D.1694",
language = "English",
volume = "E97-D",
pages = "1694--1698",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "6",

}

TY - JOUR

T1 - Utilizing global syntactic tree features for phrase reordering

AU - Lee, Yeon Soo

AU - Lee, Hyoung Gyu

AU - Rim, Hae-Chang

AU - Hwang, Young Sook

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In phrase-based statistical machine translation, long distance reordering problem is one of the most challenging issues when translating syntactically distant language pairs. In this paper, we propose a novel reordering model to solve this problem. In our model, reordering is affected by the overall structures of sentences such as listings, reduplications, and modifications as well as the relationships of adjacent phrases. To this end, we reflect global syntactic contexts including the parts that are not yet translated during the decoding process.

AB - In phrase-based statistical machine translation, long distance reordering problem is one of the most challenging issues when translating syntactically distant language pairs. In this paper, we propose a novel reordering model to solve this problem. In our model, reordering is affected by the overall structures of sentences such as listings, reduplications, and modifications as well as the relationships of adjacent phrases. To this end, we reflect global syntactic contexts including the parts that are not yet translated during the decoding process.

KW - Global syntactic tree features

KW - Phrase reordering model

KW - Phrase-based statistical machine translation

UR - http://www.scopus.com/inward/record.url?scp=84901771090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901771090&partnerID=8YFLogxK

U2 - 10.1587/transinf.E97.D.1694

DO - 10.1587/transinf.E97.D.1694

M3 - Article

AN - SCOPUS:84901771090

VL - E97-D

SP - 1694

EP - 1698

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 6

ER -