Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
サブセット探索を用いた高速なkNNニューラル機械翻訳
Search
Hiroyuki Deguchi
March 22, 2024
Research
190
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
サブセット探索を用いた高速なkNNニューラル機械翻訳
第8回AAMTセミナー
AAMT若手翻訳研究会
最優秀賞
Hiroyuki Deguchi
March 22, 2024
More Decks by Hiroyuki Deguchi
See All by Hiroyuki Deguchi
20260427 Ehime DS Seminar: MBR-CBDT Decoding
de9uch1
1
80
20260624 NLP colloquium: 単一のhubテキストがCLIPを壊す:hubnessによる埋め込みの脆弱性特定
de9uch1
2
290
20250226 NLP colloquium: "SoftMatcha: 10億単語規模コーパス検索のための柔らかくも高速なパターンマッチャー"
de9uch1
1
860
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
390
20240226_AAMT-Japio
de9uch1
0
210
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
180
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
250
My Research Environmental Setup
de9uch1
0
350
Nearest Neighbor Machine Translation
de9uch1
0
300
Other Decks in Research
See All in Research
MIRU2026 チュートリアル講演2:三次元データ処理の動向
nnchiba
8
5.3k
Sleuthcon Keynote - How Cybercriminals (ab)use AI
fr0gger
0
380
大規模言語モデルは誰を覚えているか / Who Do Large Language Models Memorize?
upura
0
210
Développer des solutions de réduction des émissions de méthane entérique : 1ers résultats Méthane 2030
institutdelelevage
PRO
0
240
Être éleveur dans un monde en transition : Comprendre les changements pour mieux les accompagner
institutdelelevage
PRO
0
130
A new deal for disabled people
resolutionfoundation
0
150
SLAMはどこまで解決されたのか?
tomonom
0
1.5k
ros2-perf-multihost: Automated Coordination Framework for Objective Architecture Evaluation in Distributed Systems
takasehideki
0
140
2025年度秋葉原ウォーカブルプロジェクト調査報告 「アキバらしいウォーカブル」とは何か
izumiyama_lab
1
250
視覚若手の会LENSって何??
mickey_0226
0
350
2026年6月_副業コンプライアンス調査_業界別リスク度分析_株式会社フクスケ.pdf
fkske
0
120
Evaluating LLM Reliability Across Facts, Evidence, and Cultures
yukiar
0
200
Featured
See All Featured
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
From π to Pie charts
rasagy
1
400
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
350
4 Signs Your Business is Dying
shpigford
187
23k
Lessons Learnt from Crawling 1000+ Websites
charlesmeaden
PRO
1
1.6k
The Hidden Cost of Media on the Web [PixelPalooza 2025]
tammyeverts
2
520
Ecommerce SEO: The Keys for Success Now & Beyond - #SERPConf2024
aleyda
1
2.2k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
930
New Earth Scene 8
popppiees
4
2.7k
Building the Perfect Custom Keyboard
takai
2
900
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
74
43k
Skip the Path - Find Your Career Trail
mkilby
1
250
Transcript
𝒌
◼ ⚫ ⚫ ◼ ⚫ (Zhang+, NAACL2018; Gu+, AAAI2018; Khandelwal+,
ICLR2021) ▶ (Nagao, 1984) ▶ ⚫ 𝑘 (Khandelwal+, ICLR2021) ▶ ▶ ▶ Guiding Neural Machine Translation with Retrieved Translation Pieces (Zhang+, NAACL2018) Search Engine Guided Neural Machine Translation (Gu+, AAAI2018) Nearest Neighbor Machine Translation (Khandelwal+, ICLR2021) A framework for a mechanical translation between Japanese and English by analogy principle (Nagao, 1984)
◼ ◼ ⚫ ⚫
𝒌 (Khandelwal+, ICLR2021) ◼ ⚫ ⚫ ⚫ ◼ ⚫ ▶
⚫ ▶ ≈ Nearest Neighbor Machine Translation (Khandelwal+, ICLR2021) 𝒙 𝒚
𝒌 (Khandelwal+, ICLR2021) 𝒌𝑖 ∈ ℝ𝐷 𝑓 𝒙, 𝒚<𝑡 ∈
ℝ𝐷 Nearest Neighbor Machine Translation (Khandelwal+, ICLR2021) ◼ 𝑘 ◼ ⚫ ⚫ 𝑝𝑘NN 𝑦𝑡 𝒙, 𝒚<𝑡 ∝ 𝑖=1 𝑘 𝟙𝑦𝑡=𝑣𝑖 exp − 𝒌𝑖 − 𝑓 𝒙, 𝒚<𝑡 2 2 𝜏 ◼ 𝑘
𝒌 ◼ (Martins+, EMNLP2022) ◼ (Meng+, ACLFindings2022) ⚫ 𝑘 𝑘
𝜆 = 0.5 𝑘 = 16 Chunk-based Nearest Neighbor Machine Translation (Martins+, EMNLP2022) Fast Nearest Neighbor Machine Translation (Meng+, ACL Findings2022)
𝒌 ◼ 𝑘 ◼ ⚫ 𝑘 (Matsui+, ACMMM2018) ⚫ 𝑘
𝑘 𝑘 Reconfigurable Inverted Index (Matsui+, ACMMM2018) 𝒌
◼ ⚫ 𝑘 ⚫ 𝑘 ◼ ◼ 𝑘
𝑛 𝑘 1 1 1 1 1 1 1 1
1
𝑛 𝑘 1 1 1 1 1 1 1 1
1
𝑛 𝑘 1 1 1 1 1 1 1 1
1
⚫ ⚫ ⚫ ⚫ ⚫ 𝑘 𝜆 = 0.5 𝑘
= 16 𝑛 = 56
𝑘 𝑘 ◼ 𝑘 ⚫ ▶ ⚫ ▶
◼ 𝑘 𝒌 𝒌
◼ ⚫ 𝑘
𝒌 𝒌 ◼ ⚫ ⚫ ◼ 𝑘 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶