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
78
Learning Dual Retrieval Module for Semi-supervised Relation Extractionの紹介
ryusuketa
0
73
動画視聴を整数倍(最大値)で_効率化するchrome extension作った
ryusuketa
0
78
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
560
Other Decks in Technology
See All in Technology
Lambda Web Adapterについて自分なりに理解してみた
smt7174
6
160
Zero Data Loss Autonomous Recovery Service サービス概要
oracle4engineer
PRO
2
7.7k
KubeCon + CloudNativeCon Japan 2025 Recap
ren510dev
1
370
ドメイン特化なCLIPモデルとデータセットの紹介
tattaka
2
580
生成AI時代 文字コードを学ぶ意義を見出せるか?
hrsued
1
810
使いたいMCPサーバーはWeb APIをラップして自分で作る #QiitaBash
bengo4com
0
1.6k
さくらのIaaS基盤のモニタリングとOpenTelemetry/OSC Hokkaido 2025
fujiwara3
2
360
赤煉瓦倉庫勉強会「Databricksを選んだ理由と、絶賛真っ只中のデータ基盤移行体験記」
ivry_presentationmaterials
2
330
AIとともに進化するエンジニアリング / Engineering-Evolving-with-AI_final.pdf
lycorptech_jp
PRO
0
160
Core Audio tapを使ったリアルタイム音声処理のお話
yuta0306
0
180
面倒な作業はAIにおまかせ。Flutter開発をスマートに効率化
ruideengineer
0
210
怖くない!はじめてのClaude Code
shinya337
0
380
Featured
See All Featured
The Cult of Friendly URLs
andyhume
79
6.5k
It's Worth the Effort
3n
185
28k
Mobile First: as difficult as doing things right
swwweet
223
9.7k
Side Projects
sachag
455
42k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
7
730
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
22k
How to Think Like a Performance Engineer
csswizardry
24
1.7k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
45
7.5k
Art, The Web, and Tiny UX
lynnandtonic
299
21k
Designing Experiences People Love
moore
142
24k
Faster Mobile Websites
deanohume
307
31k
Reflections from 52 weeks, 52 projects
jeffersonlam
351
20k
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
…