Constraint optimization approach to context based word selection

Jun Matsuno, Toru Ishida

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

9 Citations (Scopus)

Abstract

Consistent word selection in machine translation is currently realized by resolving word sense ambiguity through the context of a single sentence or neighboring sentences. However, consistent word selection over the whole article has yet to be achieved. Consistency over the whole article is extremely important when applying machine translation to collectively developed documents like Wikipedia. In this paper, we propose to consider constraints between words in the whole article based on their semantic relatedness and contextual distance. The proposed method is successfully implemented in both statistical and rule-based translators. We evaluate those systems by translating 100 articles in the English Wikipedia into Japanese. The results show that the ratio of appropriate word selection for common nouns increased to around 75% with our method, while it was around 55% without our method.

Original languageEnglish
Title of host publicationIJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence
Pages1846-1851
Number of pages6
DOIs
Publication statusPublished - 2011 Dec 1
Externally publishedYes
Event22nd International Joint Conference on Artificial Intelligence, IJCAI 2011 - Barcelona, Catalonia, Spain
Duration: 2011 Jul 162011 Jul 22

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823

Conference

Conference22nd International Joint Conference on Artificial Intelligence, IJCAI 2011
CountrySpain
CityBarcelona, Catalonia
Period11/7/1611/7/22

Fingerprint

Semantics

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Matsuno, J., & Ishida, T. (2011). Constraint optimization approach to context based word selection. In IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence (pp. 1846-1851). (IJCAI International Joint Conference on Artificial Intelligence). https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-309

Constraint optimization approach to context based word selection. / Matsuno, Jun; Ishida, Toru.

IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence. 2011. p. 1846-1851 (IJCAI International Joint Conference on Artificial Intelligence).

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

Matsuno, J & Ishida, T 2011, Constraint optimization approach to context based word selection. in IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence. IJCAI International Joint Conference on Artificial Intelligence, pp. 1846-1851, 22nd International Joint Conference on Artificial Intelligence, IJCAI 2011, Barcelona, Catalonia, Spain, 11/7/16. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-309
Matsuno J, Ishida T. Constraint optimization approach to context based word selection. In IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence. 2011. p. 1846-1851. (IJCAI International Joint Conference on Artificial Intelligence). https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-309
Matsuno, Jun ; Ishida, Toru. / Constraint optimization approach to context based word selection. IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence. 2011. pp. 1846-1851 (IJCAI International Joint Conference on Artificial Intelligence).
@inproceedings{26285cf219f04db0bf817209f82d8ea1,
title = "Constraint optimization approach to context based word selection",
abstract = "Consistent word selection in machine translation is currently realized by resolving word sense ambiguity through the context of a single sentence or neighboring sentences. However, consistent word selection over the whole article has yet to be achieved. Consistency over the whole article is extremely important when applying machine translation to collectively developed documents like Wikipedia. In this paper, we propose to consider constraints between words in the whole article based on their semantic relatedness and contextual distance. The proposed method is successfully implemented in both statistical and rule-based translators. We evaluate those systems by translating 100 articles in the English Wikipedia into Japanese. The results show that the ratio of appropriate word selection for common nouns increased to around 75{\%} with our method, while it was around 55{\%} without our method.",
author = "Jun Matsuno and Toru Ishida",
year = "2011",
month = "12",
day = "1",
doi = "10.5591/978-1-57735-516-8/IJCAI11-309",
language = "English",
isbn = "9781577355120",
series = "IJCAI International Joint Conference on Artificial Intelligence",
pages = "1846--1851",
booktitle = "IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - Constraint optimization approach to context based word selection

AU - Matsuno, Jun

AU - Ishida, Toru

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Consistent word selection in machine translation is currently realized by resolving word sense ambiguity through the context of a single sentence or neighboring sentences. However, consistent word selection over the whole article has yet to be achieved. Consistency over the whole article is extremely important when applying machine translation to collectively developed documents like Wikipedia. In this paper, we propose to consider constraints between words in the whole article based on their semantic relatedness and contextual distance. The proposed method is successfully implemented in both statistical and rule-based translators. We evaluate those systems by translating 100 articles in the English Wikipedia into Japanese. The results show that the ratio of appropriate word selection for common nouns increased to around 75% with our method, while it was around 55% without our method.

AB - Consistent word selection in machine translation is currently realized by resolving word sense ambiguity through the context of a single sentence or neighboring sentences. However, consistent word selection over the whole article has yet to be achieved. Consistency over the whole article is extremely important when applying machine translation to collectively developed documents like Wikipedia. In this paper, we propose to consider constraints between words in the whole article based on their semantic relatedness and contextual distance. The proposed method is successfully implemented in both statistical and rule-based translators. We evaluate those systems by translating 100 articles in the English Wikipedia into Japanese. The results show that the ratio of appropriate word selection for common nouns increased to around 75% with our method, while it was around 55% without our method.

UR - http://www.scopus.com/inward/record.url?scp=84864269713&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864269713&partnerID=8YFLogxK

U2 - 10.5591/978-1-57735-516-8/IJCAI11-309

DO - 10.5591/978-1-57735-516-8/IJCAI11-309

M3 - Conference contribution

SN - 9781577355120

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 1846

EP - 1851

BT - IJCAI 2011 - 22nd International Joint Conference on Artificial Intelligence

ER -