Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
An Effective Approach to Unsupervised Machine T...
Search
Ryusuke_Tanaka
November 21, 2019
Technology
0
120
An Effective Approach to Unsupervised Machine Translationの紹介
An Effective Approach to Unsupervised Machine Translationの紹介です。
教師なし翻訳に関するお話です。
Ryusuke_Tanaka
November 21, 2019
Tweet
Share
More Decks by Ryusuke_Tanaka
See All by Ryusuke_Tanaka
医師向けQAサイトのための推薦システム開発
ryusuketa
1
1.6k
Universal Decompositional Semantics on Universal Dependencies
ryusuketa
0
83
Learning Dual Retrieval Module for Semi-supervised Relation Extractionの紹介
ryusuketa
0
76
動画視聴を整数倍(最大値)で_効率化するchrome extension作った
ryusuketa
0
79
双曲空間への単語埋め込みと QAサービスでの自然言語処理を 用いた推薦システムについて
ryusuketa
0
570
Other Decks in Technology
See All in Technology
microCMS 最新リリース情報(microCMS Meetup 2025)
microcms
0
180
退屈なことはDevinにやらせよう〜〜Devin APIを使ったVisual Regression Testの自動追加〜
kawamataryo
4
800
我々は雰囲気で仕事をしている / How can we do vibe coding as well
naospon
2
220
そのコンポーネント、サーバー?クライアント?App Router開発のモヤモヤを可視化する補助輪
makotot
4
720
トヨタ生産方式(TPS)入門
recruitengineers
PRO
4
800
ドキュメントはAIの味方!スタートアップのアジャイルを加速するADR
kawauso
3
420
Webアクセシビリティ入門
recruitengineers
PRO
2
810
自社製CMSからmicroCMSへのリプレースがプロダクトグロースを加速させた話
nextbeatdev
0
220
Android Studio の 新しいAI機能を試してみよう / Try out the new AI features in Android Studio
yanzm
0
280
[CVPR2025論文読み会] Linguistics-aware Masked Image Modelingfor Self-supervised Scene Text Recognition
s_aiueo32
0
210
第4回 関東Kaggler会 [Training LLMs with Limited VRAM]
tascj
12
1.9k
イオン店舗一覧ページのパフォーマンスチューニング事例 / Performance tuning example for AEON store list page
aeonpeople
2
330
Featured
See All Featured
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.6k
Building an army of robots
kneath
306
46k
Stop Working from a Prison Cell
hatefulcrawdad
271
21k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
139
34k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
Building a Modern Day E-commerce SEO Strategy
aleyda
43
7.5k
Designing for Performance
lara
610
69k
The Pragmatic Product Professional
lauravandoore
36
6.8k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
131
19k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
7
820
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
161
15k
Transcript
An Effective Approach to Unsupervised Machine Translation
None
?/= 8E 45": 3'209 40G0AIoT< :+;F<%$6 B@-(,F.
!)#7*&>12FM2 D1 CD!)#7ML
Unsupervised Machine Translation • 87=@16Statistical Machine Translation (SMT) Neural Machine
Translation (NMT))(95/&%$ ◦ .@.0:2?>! • -B"*< .@;3,A=@4+ ◦ Word translation without parallel data.[Alexis 2017], ◦ Learning bilingual word embeddings with (almost) no bilingual data [Artetxe 2017] • !#'5/ 87=@ NMT>!4+ ◦ UNSUPERVISED MACHINE TRANSLATION USING MONOLINGUAL CORPORA ONLY [Lample2018] ◦ Unsupervised statistical machine translation [Artetxe 2018]
Supervised Machine Translation NMT Back-translation !
#"BLEU http://deeplearning.hatenablog.com/entry/back_translation#f-726c04a7
!! • D8?8B;=/@[Alexis 2017] ◦ /@*;="%$#1: ◦ ;=B/@)3& A404 6
- 5.+=A'9C9 7> ◦ +=A( , +=2<EF
SMT https://www.nhk.or.jp/strl/publica/rd/rd168/pdf/P14-25.pdf
' 1. % $ 2. &! 3. SMT$
" 4. " refinement 5. NMT(#
&9 3+ • bi-gram embedding+A8: #6>$<[Artetxe 2018] • :
100=0/ softmax &952"* (e,f8: 4 :, τ1( ?.',%!7 ) ;- …@@
2<0K,A • 3N*6 5/2<0KPO • ex. “Sunday Telegraph”
→ “The Times of London” • =H. %'#& $"&MQ4 R(8-C WaveNet:1D+@9> IF !) 2<G@7JB; LS 7JE?/ T
Unsupervised SMT • Back-translation.CE/;> ◦ DF%"&*8L @3 DFB<+4DF%"&.C •
9H7Cycle GAN !#K65= ◦ -:02I ?HA M 1 : DF'! : ,G(#'$)'! : DF7J'!
+% • '$ SMT+% .0 .0 (), +% • SMT+%
.0!/1-*&# ()2"
NMT$ • "SMT$ %# NMT$ • % NMT#
: SMT%! : NMT%!
WMT2014 seq2seq
…