The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dalam komunikasi mesin penterjemahan (MT) antara manusia dengan manusia, bukanlah satu tugas yang mudah untuk memilih bahasa dan perkhidmatan penterjemahan untuk digunakan kerana pengguna mempunyai pelbagai latar belakang dan kemahiran bahasa. Kerja kami sebelum ini memperkenalkan mekanisme terjemahan mesin seimbang terbaik (BBMT) untuk memilih bahasa dan perkhidmatan terjemahan secara automatik untuk menyamakan halangan bahasa peserta dan untuk menjamin peluang sama rata mereka dalam menyertai perbualan. Untuk menetapkan bahasa yang sesuai untuk digunakan, walau bagaimanapun, mekanisme tersebut memerlukan maklumat kemahiran bahasa peserta, biasanya markah ujian bahasa peserta. Memandangkan adalah penting untuk merahsiakan skor ujian, serta maklumat sensitif yang lain, makalah ini memperkenalkan ejen, yang menukar maklumat yang disulitkan, dan pengiraan selamat untuk memastikan ejen boleh memilih bahasa dan perkhidmatan terjemahan tanpa memusnahkan privasi. Sumbangan kami adalah untuk memperkenalkan sistem berbilang ejen dengan pengiraan selamat yang boleh melindungi privasi pengguna dalam komunikasi berbilang bahasa. Untuk pengetahuan terbaik kami, ini adalah percubaan pertama untuk memperkenalkan sistem berbilang ejen dan pengkomputeran selamat ke kawasan ini. Idea utama adalah untuk memodelkan interaksi antara ejen yang berurusan dengan data sensitif pengguna, dan untuk mengagihkan tugas pengiraan kepada tiga jenis ejen yang berbeza, bersama-sama dengan penyulitan data, jadi tiada ejen yang dapat mengakses atau memulihkan skor peserta.
Mondheera PITUXCOOSUVARN
Kyoto University
Takao NAKAGUCHI
Kyoto College of Graduate Studies for Informatics
Donghui LIN
Kyoto University
Toru ISHIDA
Waseda University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Mondheera PITUXCOOSUVARN, Takao NAKAGUCHI, Donghui LIN, Toru ISHIDA, "Privacy-Aware Best-Balanced Multilingual Communication" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 6, pp. 1288-1296, June 2020, doi: 10.1587/transinf.2019KBP0008.
Abstract: In machine translation (MT) mediated human-to-human communication, it is not an easy task to select the languages and translation services to be used as the users have various language backgrounds and skills. Our previous work introduced the best-balanced machine translation mechanism (BBMT) to automatically select the languages and translation services so as to equalize the language barriers of participants and to guarantee their equal opportunities in joining conversations. To assign proper languages to be used, however, the mechanism needs information of the participants' language skills, typically participants' language test scores. Since it is important to keep test score confidential, as well as other sensitive information, this paper introduces agents, which exchange encrypted information, and secure computation to ensure that agents can select the languages and translation services without destroying privacy. Our contribution is to introduce a multi-agent system with secure computation that can protect the privacy of users in multilingual communication. To our best knowledge, it is the first attempt to introduce multi-agent systems and secure computing to this area. The key idea is to model interactions among agents who deal with user's sensitive data, and to distribute calculation tasks to three different types of agents, together with data encryption, so no agent is able to access or recover participants' score.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019KBP0008/_p
Salinan
@ARTICLE{e103-d_6_1288,
author={Mondheera PITUXCOOSUVARN, Takao NAKAGUCHI, Donghui LIN, Toru ISHIDA, },
journal={IEICE TRANSACTIONS on Information},
title={Privacy-Aware Best-Balanced Multilingual Communication},
year={2020},
volume={E103-D},
number={6},
pages={1288-1296},
abstract={In machine translation (MT) mediated human-to-human communication, it is not an easy task to select the languages and translation services to be used as the users have various language backgrounds and skills. Our previous work introduced the best-balanced machine translation mechanism (BBMT) to automatically select the languages and translation services so as to equalize the language barriers of participants and to guarantee their equal opportunities in joining conversations. To assign proper languages to be used, however, the mechanism needs information of the participants' language skills, typically participants' language test scores. Since it is important to keep test score confidential, as well as other sensitive information, this paper introduces agents, which exchange encrypted information, and secure computation to ensure that agents can select the languages and translation services without destroying privacy. Our contribution is to introduce a multi-agent system with secure computation that can protect the privacy of users in multilingual communication. To our best knowledge, it is the first attempt to introduce multi-agent systems and secure computing to this area. The key idea is to model interactions among agents who deal with user's sensitive data, and to distribute calculation tasks to three different types of agents, together with data encryption, so no agent is able to access or recover participants' score.},
keywords={},
doi={10.1587/transinf.2019KBP0008},
ISSN={1745-1361},
month={June},}
Salinan
TY - JOUR
TI - Privacy-Aware Best-Balanced Multilingual Communication
T2 - IEICE TRANSACTIONS on Information
SP - 1288
EP - 1296
AU - Mondheera PITUXCOOSUVARN
AU - Takao NAKAGUCHI
AU - Donghui LIN
AU - Toru ISHIDA
PY - 2020
DO - 10.1587/transinf.2019KBP0008
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2020
AB - In machine translation (MT) mediated human-to-human communication, it is not an easy task to select the languages and translation services to be used as the users have various language backgrounds and skills. Our previous work introduced the best-balanced machine translation mechanism (BBMT) to automatically select the languages and translation services so as to equalize the language barriers of participants and to guarantee their equal opportunities in joining conversations. To assign proper languages to be used, however, the mechanism needs information of the participants' language skills, typically participants' language test scores. Since it is important to keep test score confidential, as well as other sensitive information, this paper introduces agents, which exchange encrypted information, and secure computation to ensure that agents can select the languages and translation services without destroying privacy. Our contribution is to introduce a multi-agent system with secure computation that can protect the privacy of users in multilingual communication. To our best knowledge, it is the first attempt to introduce multi-agent systems and secure computing to this area. The key idea is to model interactions among agents who deal with user's sensitive data, and to distribute calculation tasks to three different types of agents, together with data encryption, so no agent is able to access or recover participants' score.
ER -