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
1.7k
Universal Decompositional Semantics on Universal Dependencies
ryusuketa
0
85
Learning Dual Retrieval Module for Semi-supervised Relation Extractionの紹介
ryusuketa
0
80
動画視聴を整数倍(最大値)で_効率化するchrome extension作った
ryusuketa
0
80
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
580
Other Decks in Technology
See All in Technology
生成AIとM5Stack / M5 Japan Tour 2025 Autumn 東京
you
PRO
0
240
Where will it converge?
ibknadedeji
0
200
The Cake Is a Lie... And So Is Your Login’s Accessibility
leichteckig
0
110
綺麗なデータマートをつくろう_データ整備を前向きに考える会 / Let's create clean data mart
brainpadpr
3
380
Performance Insights 廃止から Database Insights 利用へ/transition-from-performance-insights-to-database-insights
emiki
0
180
これがLambdaレス時代のChatOpsだ!実例で学ぶAmazon Q Developerカスタムアクション活用法
iwamot
PRO
6
940
プロポーザルのコツ ~ Kaigi on Rails 2025 初参加で3名の登壇を実現 ~
naro143
1
210
Azure Well-Architected Framework入門
tomokusaba
1
350
Codexとも仲良く。CodeRabbit CLIの紹介
moongift
PRO
0
120
カンファレンスに託児サポートがあるということ / Having Childcare Support at Conferences
nobu09
1
520
能登半島災害現場エンジニアクロストーク 【JAWS FESTA 2025 in 金沢】
ditccsugii
0
370
『OCI で学ぶクラウドネイティブ 実践 × 理論ガイド』 書籍概要
oracle4engineer
PRO
3
200
Featured
See All Featured
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
30
2.7k
Unsuck your backbone
ammeep
671
58k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
7
900
The World Runs on Bad Software
bkeepers
PRO
72
11k
It's Worth the Effort
3n
187
28k
jQuery: Nuts, Bolts and Bling
dougneiner
65
7.9k
How to Ace a Technical Interview
jacobian
280
24k
Become a Pro
speakerdeck
PRO
29
5.5k
For a Future-Friendly Web
brad_frost
180
9.9k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Navigating Team Friction
lara
190
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
…