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
77
Learning Dual Retrieval Module for Semi-supervised Relation Extractionの紹介
ryusuketa
0
72
動画視聴を整数倍(最大値)で_効率化するchrome extension作った
ryusuketa
0
77
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
550
Other Decks in Technology
See All in Technology
Witchcraft for Memory
pocke
1
300
Observability infrastructure behind the trillion-messages scale Kafka platform
lycorptech_jp
PRO
0
140
データプラットフォーム技術におけるメダリオンアーキテクチャという考え方/DataPlatformWithMedallionArchitecture
smdmts
5
630
生成AIでwebアプリケーションを作ってみた
tajimon
2
150
変化する開発、進化する体系時代に適応するソフトウェアエンジニアの知識と考え方(JaSST'25 Kansai)
mizunori
1
210
Yamla: Rustでつくるリアルタイム性を追求した機械学習基盤 / Yamla: A Rust-Based Machine Learning Platform Pursuing Real-Time Capabilities
lycorptech_jp
PRO
3
120
プロダクトエンジニアリング組織への歩み、その現在地 / Our journey to becoming a product engineering organization
hiro_torii
0
130
OpenHands🤲にContributeしてみた
kotauchisunsun
1
430
PHP開発者のためのSOLID原則再入門 #phpcon / PHP Conference Japan 2025
shogogg
4
730
GitHub Copilot の概要
tomokusaba
1
130
低レイヤを知りたいPHPerのためのCコンパイラ作成入門 完全版 / Building a C Compiler for PHPers Who Want to Dive into Low-Level Programming - Expanded
tomzoh
4
3.2k
LinkX_GitHubを基点にした_AI時代のプロジェクトマネジメント.pdf
iotcomjpadmin
0
170
Featured
See All Featured
Principles of Awesome APIs and How to Build Them.
keavy
126
17k
Gamification - CAS2011
davidbonilla
81
5.3k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
130
19k
Unsuck your backbone
ammeep
671
58k
The Pragmatic Product Professional
lauravandoore
35
6.7k
Documentation Writing (for coders)
carmenintech
72
4.9k
Rebuilding a faster, lazier Slack
samanthasiow
82
9.1k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
8
790
GraphQLとの向き合い方2022年版
quramy
48
14k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
StorybookのUI Testing Handbookを読んだ
zakiyama
30
5.8k
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
…