Presentation 2019-03-07
Coherence-based Spoken Machine Translation Recognition: Towards an Efficient Gateway to Detect Untrusted Information
Nguyen Son Hoang Quoc, Tran Phuong Thao, Seira Hidano, Shinsaku Kiyomoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The machine-translated text is playing an important role in modern life which establishes wide communication among various communities using different languages. However, attackers are exploiting it to create a lot of untrusted information. Therefore, how to detect such information becomes a great demand in preventing the over-belief in this artificial content. Previous methods have measured the coherence of words among sentences of a paragraph. However, they ignore relationships of words in an individual sentence. We have thus developed a method by matching similar words within a paragraph for estimating the paragraph-level coherence, which is used to identify machine-translated text. The experiments on 4000 English human-generated and 4000 English machine-translated paragraphs show that our coherence-based method achieves high accuracy 87.0% and 98.2% which outperforms the previous methods best accuracy 72.4% and 96.6% in German and Japanese, respectively.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Untrusted information detectionMachine translationHuman-created textCoherenceSimilar words matching
Paper # IT2018-77,ISEC2018-83,WBS2018-78
Date of Issue 2019-02-28 (IT, ISEC, WBS)

Conference Information
Committee IT / ISEC / WBS
Conference Date 2019/3/7(2days)
Place (in Japanese) (See Japanese page)
Place (in English) University of Electro-Communications
Topics (in Japanese) (See Japanese page)
Topics (in English) joint meeting of IT, ISEC, and WBS
Chair Jun Muramatsu(NTT) / Atsushi Fujioka(Kanagawa Univ.) / Minoru Okada(NAIST)
Vice Chair Tadashi Wadayama(Nagoya Inst. of Tech.) / Shiho Moriai(NICT) / Shoichi Hirose(Univ. of Fukui) / Koji Ohuchi(Shizuoka Univ.) / Kenichi Takizawa(NICT)
Secretary Tadashi Wadayama(Nagano Pref Inst. of Tech.) / Shiho Moriai(UEC) / Shoichi Hirose(Tokai Univ.) / Koji Ohuchi(NICT) / Kenichi Takizawa(Ibaraki Univ.)
Assistant Takahiro Yoshida(Yokohama College of Commerce) / Kazunari Omote(Tsukuba Univ.) / Yuuji Suga(IIJ) / Ryohei Nakamura(National Defense Academy) / Duong Quang Thang(NAIST)

Paper Information
Registration To Technical Committee on Information Theory / Technical Committee on Information Security / Technical Committee on Wideband System
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Coherence-based Spoken Machine Translation Recognition: Towards an Efficient Gateway to Detect Untrusted Information
Sub Title (in English)
Keyword(1) Untrusted information detectionMachine translationHuman-created textCoherenceSimilar words matching
1st Author's Name Nguyen Son Hoang Quoc
1st Author's Affiliation KDDI Research, Inc.(KDDI Research)
2nd Author's Name Tran Phuong Thao
2nd Author's Affiliation KDDI Research, Inc.(KDDI Research)
3rd Author's Name Seira Hidano
3rd Author's Affiliation KDDI Research, Inc.(KDDI Research)
4th Author's Name Shinsaku Kiyomoto
4th Author's Affiliation KDDI Research, Inc.(KDDI Research)
Date 2019-03-07
Paper # IT2018-77,ISEC2018-83,WBS2018-78
Volume (vol) vol.118
Number (no) IT-477,ISEC-478,WBS-479
Page pp.pp.13-19(IT), pp.13-19(ISEC), pp.13-19(WBS),
#Pages 7
Date of Issue 2019-02-28 (IT, ISEC, WBS)