Context-based approach for pivot translation services

Rie Tanaka, Yohei Murakami, Toru Ishida

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

20 Citations (Scopus)

Abstract

Machine translation services available on the Web are becoming increasingly popular. However, a pivot translation service is required to realize translations between non-English languages by cascading different translation services via English. As a result, the meaning of words often drifts due to the inconsistency, asymmetry and intransitivity of word selections among translation services. In this paper, we propose context-based coordination to maintain the consistency of word meanings during pivot translation services. First, we propose a method to automatically generate multilingual equivalent terms based on bilingual dictionaries and use generated terms to propagate context among combined translation services. Second, we show a multiagent architecture as one way of implementation, wherein a coordinator agent gathers and propagates context from/to a translation agent. We generated trilingual equivalent noun terms and implemented a Japanese-to-German-and-back translation, cascading into four translation services. The evaluation results showed that the generated terms can cover over 58% of all nouns. The translation quality was improved by 40% for all sentences, and the quality rating for all sentences increased by an average of 0.47 points on a five-point scale. These results indicate that we can realize consistent pivot translation services through context-based coordination based on existing services.

Original languageEnglish
Title of host publicationIJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence
Pages1555-1561
Number of pages7
Publication statusPublished - 2009 Dec 1
Externally publishedYes
Event21st International Joint Conference on Artificial Intelligence, IJCAI-09 - Pasadena, CA, United States
Duration: 2009 Jul 112009 Jul 17

Publication series

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

Other

Other21st International Joint Conference on Artificial Intelligence, IJCAI-09
CountryUnited States
CityPasadena, CA
Period09/7/1109/7/17

Fingerprint

Glossaries

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Tanaka, R., Murakami, Y., & Ishida, T. (2009). Context-based approach for pivot translation services. In IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence (pp. 1555-1561). (IJCAI International Joint Conference on Artificial Intelligence).

Context-based approach for pivot translation services. / Tanaka, Rie; Murakami, Yohei; Ishida, Toru.

IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence. 2009. p. 1555-1561 (IJCAI International Joint Conference on Artificial Intelligence).

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

Tanaka, R, Murakami, Y & Ishida, T 2009, Context-based approach for pivot translation services. in IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence. IJCAI International Joint Conference on Artificial Intelligence, pp. 1555-1561, 21st International Joint Conference on Artificial Intelligence, IJCAI-09, Pasadena, CA, United States, 09/7/11.
Tanaka R, Murakami Y, Ishida T. Context-based approach for pivot translation services. In IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence. 2009. p. 1555-1561. (IJCAI International Joint Conference on Artificial Intelligence).
Tanaka, Rie ; Murakami, Yohei ; Ishida, Toru. / Context-based approach for pivot translation services. IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence. 2009. pp. 1555-1561 (IJCAI International Joint Conference on Artificial Intelligence).
@inproceedings{09be0b8e87fd4f6c904cfcbdaadff2c0,
title = "Context-based approach for pivot translation services",
abstract = "Machine translation services available on the Web are becoming increasingly popular. However, a pivot translation service is required to realize translations between non-English languages by cascading different translation services via English. As a result, the meaning of words often drifts due to the inconsistency, asymmetry and intransitivity of word selections among translation services. In this paper, we propose context-based coordination to maintain the consistency of word meanings during pivot translation services. First, we propose a method to automatically generate multilingual equivalent terms based on bilingual dictionaries and use generated terms to propagate context among combined translation services. Second, we show a multiagent architecture as one way of implementation, wherein a coordinator agent gathers and propagates context from/to a translation agent. We generated trilingual equivalent noun terms and implemented a Japanese-to-German-and-back translation, cascading into four translation services. The evaluation results showed that the generated terms can cover over 58{\%} of all nouns. The translation quality was improved by 40{\%} for all sentences, and the quality rating for all sentences increased by an average of 0.47 points on a five-point scale. These results indicate that we can realize consistent pivot translation services through context-based coordination based on existing services.",
author = "Rie Tanaka and Yohei Murakami and Toru Ishida",
year = "2009",
month = "12",
day = "1",
language = "English",
isbn = "9781577354260",
series = "IJCAI International Joint Conference on Artificial Intelligence",
pages = "1555--1561",
booktitle = "IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence",

}

TY - GEN

T1 - Context-based approach for pivot translation services

AU - Tanaka, Rie

AU - Murakami, Yohei

AU - Ishida, Toru

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Machine translation services available on the Web are becoming increasingly popular. However, a pivot translation service is required to realize translations between non-English languages by cascading different translation services via English. As a result, the meaning of words often drifts due to the inconsistency, asymmetry and intransitivity of word selections among translation services. In this paper, we propose context-based coordination to maintain the consistency of word meanings during pivot translation services. First, we propose a method to automatically generate multilingual equivalent terms based on bilingual dictionaries and use generated terms to propagate context among combined translation services. Second, we show a multiagent architecture as one way of implementation, wherein a coordinator agent gathers and propagates context from/to a translation agent. We generated trilingual equivalent noun terms and implemented a Japanese-to-German-and-back translation, cascading into four translation services. The evaluation results showed that the generated terms can cover over 58% of all nouns. The translation quality was improved by 40% for all sentences, and the quality rating for all sentences increased by an average of 0.47 points on a five-point scale. These results indicate that we can realize consistent pivot translation services through context-based coordination based on existing services.

AB - Machine translation services available on the Web are becoming increasingly popular. However, a pivot translation service is required to realize translations between non-English languages by cascading different translation services via English. As a result, the meaning of words often drifts due to the inconsistency, asymmetry and intransitivity of word selections among translation services. In this paper, we propose context-based coordination to maintain the consistency of word meanings during pivot translation services. First, we propose a method to automatically generate multilingual equivalent terms based on bilingual dictionaries and use generated terms to propagate context among combined translation services. Second, we show a multiagent architecture as one way of implementation, wherein a coordinator agent gathers and propagates context from/to a translation agent. We generated trilingual equivalent noun terms and implemented a Japanese-to-German-and-back translation, cascading into four translation services. The evaluation results showed that the generated terms can cover over 58% of all nouns. The translation quality was improved by 40% for all sentences, and the quality rating for all sentences increased by an average of 0.47 points on a five-point scale. These results indicate that we can realize consistent pivot translation services through context-based coordination based on existing services.

UR - http://www.scopus.com/inward/record.url?scp=78751693452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78751693452&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577354260

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 1555

EP - 1561

BT - IJCAI-09 - Proceedings of the 21st International Joint Conference on Artificial Intelligence

ER -