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
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
170
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
260624_NLP-colloquium: Hubness
de9uch1
0
110
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
800
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
360
20240226_AAMT-Japio
de9uch1
0
200
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
160
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
220
My Research Environmental Setup
de9uch1
0
340
Nearest Neighbor Machine Translation
de9uch1
0
290
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
310
Other Decks in Research
See All in Research
Sleuthcon Keynote - How Cybercriminals (ab)use AI
fr0gger
0
260
[CV勉強会@関東 CVPR2026] PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow / kantocv 67th CVPR 2026
shunk031
0
170
nlp2026 In-Context Learningに基づく経路案内のための地理的知識の活用方法に関する検討
takashiinui
0
110
SoftMatcha 2: 1兆語規模コーパスの超高速かつ柔らかい検索
e869120_sub
7
3.6k
AY 2026 Guide to Academic Writing Using Generative AI - Workshop
ks91
PRO
0
140
Cross-Media Human-Information Interaction
signer
PRO
0
130
進学校の生徒にはア行の苗字が多いのか
ozekinote
0
480
GLIM とMegaParticles:正規分布近似の限界とタイトカップリング&パーティクルフィルタの進展 / GLIM and MegaParticles : Progress of the distribution representation in SLAM
koide3
0
610
多様なデータを許容し学習し続ける模倣学習 / Advanced Imitation Learning for VLA
prinlab
0
250
ScoreMatchingRiesz for Automatic Debiased Machine Learning and Policy Path Estimation with an Application to Japanese Monetary Policy Evaluation
masakat0
0
310
Model Discovery and Graph Simulation: A Lightweight Gateway to Chaos Engineering
anatolykr
0
230
Sequences of Logits Reveal the Low Rank Structure of Language Models
sansantech
PRO
1
290
Featured
See All Featured
Public Speaking Without Barfing On Your Shoes - THAT 2023
reverentgeek
1
460
Tell your own story through comics
letsgokoyo
1
1k
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
1
410
Darren the Foodie - Storyboard
khoart
PRO
3
3.4k
My Coaching Mixtape
mlcsv
0
170
Into the Great Unknown - MozCon
thekraken
41
2.6k
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
190
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.8k
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
220
Digital Ethics as a Driver of Design Innovation
axbom
PRO
1
350
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
440
Embracing the Ebb and Flow
colly
88
5.1k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶