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
180
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
38
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
280
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
840
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
380
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
240
My Research Environmental Setup
de9uch1
0
350
Nearest Neighbor Machine Translation
de9uch1
0
300
Other Decks in Research
See All in Research
PHTalks Bengaluru - SSRF When All Else Fails
dk999
0
1.2k
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
330
COMETAを用いたデータ民主化運動の歴史
sazimai
0
250
Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance
satai
3
130
人間中心の意思決定支援AI
yukinobaba
PRO
7
4.1k
コーディングエージェントとABNを再考
hf149
2
860
2026年 オープンキャンパス 研究室紹介
junkurihara
0
210
医療LLMの現在地〜最新研究から社会実装までを考える〜
kento1109
1
1.7k
ros2-perf-multihost: 分散システムにおける客観的なアーキテクチャ評価フレームワーク
takasehideki
0
270
データサイエンティストの就労意識~2015 → 2026 一般(個人)会員アンケートより
datascientistsociety
PRO
0
860
クラウド・AI 時代の研究開発 DX / R&D Digital Transformation
hariby
0
140
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
870
Featured
See All Featured
Technical Leadership for Architectural Decision Making
baasie
3
570
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.3k
Building Flexible Design Systems
yeseniaperezcruz
330
41k
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
200
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
42k
JAMstack: Web Apps at Ludicrous Speed - All Things Open 2022
reverentgeek
1
600
Jess Joyce - The Pitfalls of Following Frameworks
techseoconnect
PRO
1
420
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.8k
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
710
Statistics for Hackers
jakevdp
799
230k
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
63
46k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
12
1.3k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶