Translation agent

Chunqi Shi, Toru Ishida, Donghui Lin

研究成果: Chapter

抄録

When applying Language Grid for multilingual communication support, it is important to understand the effects of the machine translation service. To support the users in multilingual communication, it is recognized that machine translation service used is not a perfect transparent-channel to users. We present agent metaphor as a novel interactive way to promote the efficiency of communication in using machine translation service. It will reduce the communication breaks caused by translation errors. We propose to shift from the transparent-channel metaphor to the agent metaphor, which motives the interactions between the users and the machine translator. Following this paradigm shifting, the agent should encourage the dialog participants to collaborate, as their interactivity will be helpful in reducing the number of translation errors. We examined the translation issues raised by multilingual communication, and analyzed the impact of interactivity on the elimination of translation errors. We proposed an implementation of the agent protocol for interactivity promotion. We designed the architecture of our agent, analyzed the interaction process, and provided an example of preparing repair strategy. We conducted an English–Chinese communication task experiment on tangram arrangement. The experiment shows that compared to the transparent-channel metaphor, our agent metaphor reduces human communication effort by 21.6%.

元の言語English
ホスト出版物のタイトルCognitive Technologies
出版者Springer-Verlag
ページ175-192
ページ数18
エディション9789811077920
DOI
出版物ステータスPublished - 2018 1 1
外部発表Yes

出版物シリーズ

名前Cognitive Technologies
番号9789811077920
ISSN(印刷物)1611-2482

Fingerprint

Communication
Repair
Experiments

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

これを引用

Shi, C., Ishida, T., & Lin, D. (2018). Translation agent. : Cognitive Technologies (9789811077920 版, pp. 175-192). (Cognitive Technologies; 番号 9789811077920). Springer-Verlag. https://doi.org/10.1007/978-981-10-7793-7_11

Translation agent. / Shi, Chunqi; Ishida, Toru; Lin, Donghui.

Cognitive Technologies. 9789811077920. 編 Springer-Verlag, 2018. p. 175-192 (Cognitive Technologies; 番号 9789811077920).

研究成果: Chapter

Shi, C, Ishida, T & Lin, D 2018, Translation agent. : Cognitive Technologies. 9789811077920 Edn, Cognitive Technologies, 番号 9789811077920, Springer-Verlag, pp. 175-192. https://doi.org/10.1007/978-981-10-7793-7_11
Shi C, Ishida T, Lin D. Translation agent. : Cognitive Technologies. 9789811077920 版 Springer-Verlag. 2018. p. 175-192. (Cognitive Technologies; 9789811077920). https://doi.org/10.1007/978-981-10-7793-7_11
Shi, Chunqi ; Ishida, Toru ; Lin, Donghui. / Translation agent. Cognitive Technologies. 9789811077920. 版 Springer-Verlag, 2018. pp. 175-192 (Cognitive Technologies; 9789811077920).
@inbook{cdc05e23429b408bb8922b1ca5cf8d11,
title = "Translation agent",
abstract = "When applying Language Grid for multilingual communication support, it is important to understand the effects of the machine translation service. To support the users in multilingual communication, it is recognized that machine translation service used is not a perfect transparent-channel to users. We present agent metaphor as a novel interactive way to promote the efficiency of communication in using machine translation service. It will reduce the communication breaks caused by translation errors. We propose to shift from the transparent-channel metaphor to the agent metaphor, which motives the interactions between the users and the machine translator. Following this paradigm shifting, the agent should encourage the dialog participants to collaborate, as their interactivity will be helpful in reducing the number of translation errors. We examined the translation issues raised by multilingual communication, and analyzed the impact of interactivity on the elimination of translation errors. We proposed an implementation of the agent protocol for interactivity promotion. We designed the architecture of our agent, analyzed the interaction process, and provided an example of preparing repair strategy. We conducted an English–Chinese communication task experiment on tangram arrangement. The experiment shows that compared to the transparent-channel metaphor, our agent metaphor reduces human communication effort by 21.6{\%}.",
keywords = "Interactivity, Machine translation mediated communication, Repair",
author = "Chunqi Shi and Toru Ishida and Donghui Lin",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-981-10-7793-7_11",
language = "English",
series = "Cognitive Technologies",
publisher = "Springer-Verlag",
number = "9789811077920",
pages = "175--192",
booktitle = "Cognitive Technologies",
edition = "9789811077920",

}

TY - CHAP

T1 - Translation agent

AU - Shi, Chunqi

AU - Ishida, Toru

AU - Lin, Donghui

PY - 2018/1/1

Y1 - 2018/1/1

N2 - When applying Language Grid for multilingual communication support, it is important to understand the effects of the machine translation service. To support the users in multilingual communication, it is recognized that machine translation service used is not a perfect transparent-channel to users. We present agent metaphor as a novel interactive way to promote the efficiency of communication in using machine translation service. It will reduce the communication breaks caused by translation errors. We propose to shift from the transparent-channel metaphor to the agent metaphor, which motives the interactions between the users and the machine translator. Following this paradigm shifting, the agent should encourage the dialog participants to collaborate, as their interactivity will be helpful in reducing the number of translation errors. We examined the translation issues raised by multilingual communication, and analyzed the impact of interactivity on the elimination of translation errors. We proposed an implementation of the agent protocol for interactivity promotion. We designed the architecture of our agent, analyzed the interaction process, and provided an example of preparing repair strategy. We conducted an English–Chinese communication task experiment on tangram arrangement. The experiment shows that compared to the transparent-channel metaphor, our agent metaphor reduces human communication effort by 21.6%.

AB - When applying Language Grid for multilingual communication support, it is important to understand the effects of the machine translation service. To support the users in multilingual communication, it is recognized that machine translation service used is not a perfect transparent-channel to users. We present agent metaphor as a novel interactive way to promote the efficiency of communication in using machine translation service. It will reduce the communication breaks caused by translation errors. We propose to shift from the transparent-channel metaphor to the agent metaphor, which motives the interactions between the users and the machine translator. Following this paradigm shifting, the agent should encourage the dialog participants to collaborate, as their interactivity will be helpful in reducing the number of translation errors. We examined the translation issues raised by multilingual communication, and analyzed the impact of interactivity on the elimination of translation errors. We proposed an implementation of the agent protocol for interactivity promotion. We designed the architecture of our agent, analyzed the interaction process, and provided an example of preparing repair strategy. We conducted an English–Chinese communication task experiment on tangram arrangement. The experiment shows that compared to the transparent-channel metaphor, our agent metaphor reduces human communication effort by 21.6%.

KW - Interactivity

KW - Machine translation mediated communication

KW - Repair

UR - http://www.scopus.com/inward/record.url?scp=85042562811&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042562811&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-7793-7_11

DO - 10.1007/978-981-10-7793-7_11

M3 - Chapter

AN - SCOPUS:85042562811

T3 - Cognitive Technologies

SP - 175

EP - 192

BT - Cognitive Technologies

PB - Springer-Verlag

ER -