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
EMNLP2015読み会:Effective Approaches to Attention-...
Search
tkng
October 24, 2015
Research
2
3.9k
EMNLP2015読み会:Effective Approaches to Attention-based Neural Machine Translation
tkng
October 24, 2015
Tweet
Share
More Decks by tkng
See All by tkng
LSTMを用いた自然言語処理について
tkng
3
3.7k
自然言語処理と深層学習の最先端
tkng
16
7.6k
basis-of-optimization.pdf
tkng
1
1.3k
Other Decks in Research
See All in Research
渋谷Well-beingアンケート調査結果
shibuyasmartcityassociation
0
400
AWS 音声基盤モデル トーク解析AI MiiTelの音声処理について
ken57
0
140
メタヒューリスティクスに基づく汎用線形整数計画ソルバーの開発
snowberryfield
3
780
資産間の相関関係を頑健に評価する指標を用いたファクターアローケーション戦略の構築
nomamist
0
130
文書画像のデータ化における VLM活用 / Use of VLM in document image data conversion
sansan_randd
2
530
新規のC言語処理系を実装することによる 組込みシステム研究にもたらす価値 についての考察
zacky1972
1
320
PostgreSQLにおける分散トレーシングの現在 - 第50回PostgreSQLアンカンファレンス
seinoyu
0
230
ECCV2024読み会: Minimalist Vision with Freeform Pixels
hsmtta
1
420
Global Evidence Summit (GES) 参加報告
daimoriwaki
0
240
Whoisの闇
hirachan
3
300
Retrieval of Hurricane Rain Rate From SAR Images Based on Artificial Neural Network
satai
3
140
Gemini と Looker で営業DX をドライブする / Driving Sales DX with Gemini and Looker
sansan_randd
0
120
Featured
See All Featured
The Cult of Friendly URLs
andyhume
78
6.2k
Building Your Own Lightsaber
phodgson
104
6.2k
Building Adaptive Systems
keathley
40
2.4k
Visualization
eitanlees
146
15k
VelocityConf: Rendering Performance Case Studies
addyosmani
328
24k
Optimising Largest Contentful Paint
csswizardry
34
3.1k
Become a Pro
speakerdeck
PRO
26
5.2k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
29
1k
The Language of Interfaces
destraynor
156
24k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
32
2.1k
A Tale of Four Properties
chriscoyier
158
23k
Why You Should Never Use an ORM
jnunemaker
PRO
55
9.2k
Transcript
Effective Approaches to Attention-based Neural Machine Translation Authors: Minh-Thang LuongɹHieu
PhamɹChristopher D. Manning ಡΉਓ: ಙӬ೭ ਤશͯ͜ͷจ͔ΒҾ༻ &./-1ಡΈձ
ࣗݾհɿಙӬ೭ • Twitter ID: @tkng • εϚʔτχϡʔεגࣜձࣾͰNLPͬͯ·͢
ࠓͷจʁ • Effective Approaches to Attention-based Neural Machine Translation •
ڈ͙Β͍͔ΒྲྀߦΓ࢝Ίͨseq2seqܥͷख ๏ͷ֦ு
Seq2seq modelͱʁ • Encoder/Decoder modelͱݴ͏ • ༁ݩͷจΛݻఆͷϕΫτϧʹΤϯίʔυ ͯ͠ɺ͔ͦ͜Β༁ޙͷจΛσίʔυ͢Δ • ՄมͷσʔλऔΓѻ͍͕͍͠ͷͰɺ
͑ͯݻఆʹͯ͠͠·͏ͱ͍͏ൃ
Ͳ͏ͬͯݻఆʹΤϯίʔυ ͢Δͷʁ • recurrent neural networkΛ͏ • http://colah.github.io/posts/2015-08-Understanding-LSTMs/ • http://kaishengtai.github.io/static/slides/treelstm-acl2015.pdf
• LSTM = recurrent neural networkͷҰछ
Seq2seqϞσϧͰͷ༁
Seq2seq·ͰͷಓͷΓ (1) • Recurrent Continuous Translation Models (EMNLP2013) • Learning
Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation (EMNLP2014)
Seq2seq·ͰͷಓͷΓ (2) • Sequence to Sequence Learning with Neural Networks
(NIPS2014) • ൺֱతγϯϓϧͳStacked LSTM͕ྑ͍ੑೳΛ ࣔ͢͜ͱ͕࣮ݧͰࣔ͞Εͨ • ϏʔϜαʔνɺٯॱͰͷೖྗɺΞϯαϯϒϧ ͷ3छྨͷ͕ೖ͍ͬͯΔ
Seq2seqϞσϧͷऑ • จʹऑ͍ • ݻ༗໊ࢺ͕ೖΕସΘΔ
AttentionʹΑΔվળ [Bahdanau+ 2015] • DecodeͷࡍͷContextʹEncodeͷࡍͷ֤࣌ࠁ ʹ͓͚ΔӅΕঢ়ଶͷॏΈ͖Λ༻͍Δ • ॏΈࣗମRNNͰܭࢉ͢Δ
ࠓճͷจͷߩݙ • ৽͍͠attention (local attention) ΛఏҊͨ͠ • ༁ݩจʹ͓͍ͯɺҐஔɹ͔ΒલޙD୯ޠ ͷӅΕঢ়ଶͷॏΈ͖ΛऔΔ •
ॏΈͷܭࢉglobal attentionͷ߹ͱಉ༷ • ɹ1ͭͣͭਐΊ͍ͯ͘߹ʢlocal-mʣ ͱɺ͜ΕࣗମRNNʹ͢Δ߹ʢlocal- pʣͷ2ͭΛ࣮ݧ͍ͯ͠Δ pt pt
local attention
local attentionͷҹ • ޠॱ͕ࣅ͍ͯΔݴޠؒͰͷ༁ͳΒɺ໌Β͔ ʹ͜ͷํ͕ྑͦ͞͏ • ӳΈ͍ͨʹޠॱ͕େ͖͘ҧ͏߹ɺ Ґஔɹͷਪఆࣗମ͕͍͠λεΫʹͳͬͪΌ ͍ͦ͏… pt
࣮ݧ݁ՌɿWMT'14
࣮ݧ݁ՌɿWMT'14 • Α͘ݟΔͱɺlocal attentionͰͷੑೳ্ +0.9ϙΠϯτ • ଞͷςΫχοΫͰՔ͍ͰΔϙΠϯτ͕ଟ͍
࣮ݧ݁ՌɿWMT'15
͍͔ͭ͘༁αϯϓϧ
·ͱΊ • Seq2seqϞσϧͷ֦ுͱͯ͠ɺlocal attention ΛఏҊͨ͠ • ఏҊख๏͍͔ͭ͘ͷ࣮ݧʹ͓͍ͯɺState of the artͷੑೳΛୡͨ͠
ײ • Local attentionΛඍ • ྨࣅ͢Δख๏ͱ۩ମతʹͲ͏ҧ͏͔͕໌շʹ ॻ͔Ε͓ͯΓɺಡΈ͔ͬͨ͢ • AttentionΛཧղͰ͖ͯΑ͔ͬͨʢখฒײʣ