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
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
260624_NLP-colloquium: Hubness
de9uch1
1
170
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
810
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
370
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
170
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
230
My Research Environmental Setup
de9uch1
0
350
Nearest Neighbor Machine Translation
de9uch1
0
290
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
320
Other Decks in Research
See All in Research
Cross-Media Human-Information Interaction
signer
PRO
0
170
RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
satai
3
460
PGDM: Physically Guided Diffusion Model for L Downscaling
satai
3
400
言語モデルから言語について語る際に押さえておきたいこと
eumesy
PRO
7
2.5k
「AIとWhyを深堀る」をAIと深堀る
iflection
0
560
typst の使い方:言語学を研究する学生のために
gitomochang
0
540
SOTAのさらに先へ:厳しい推論制約下での高性能モデルのPost-Training
analokmaus
0
1.4k
ScoreMatchingRiesz for Automatic Debiased Machine Learning and Policy Path Estimation with an Application to Japanese Monetary Policy Evaluation
masakat0
0
320
議論 学術ムーブメントを成功させるために何が必要なのだろうか
rmaruy
0
110
2026年版中小企業白書・小規模企業白書の概要
ozekinote
0
150
Using our influence and power for patient safety
helenbevan
0
390
Harness Engineering and Al Agent
kzinmr
3
1.9k
Featured
See All Featured
Utilizing Notion as your number one productivity tool
mfonobong
4
540
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
400
Site-Speed That Sticks
csswizardry
13
1.4k
How Software Deployment tools have changed in the past 20 years
geshan
1
34k
The Curious Case for Waylosing
cassininazir
1
450
HDC tutorial
michielstock
2
790
How to Talk to Developers About Accessibility
jct
2
510
Getting science done with accelerated Python computing platforms
jacobtomlinson
2
420
Designing Experiences People Love
moore
143
24k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
37
6.5k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
2.9k
Scaling GitHub
holman
464
140k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶