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
0
160
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
Tweet
Share
More Decks by Hiroyuki Deguchi
See All by Hiroyuki Deguchi
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
0
700
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
320
20240226_AAMT-Japio
de9uch1
0
170
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
150
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
200
My Research Environmental Setup
de9uch1
0
330
Nearest Neighbor Machine Translation
de9uch1
0
280
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
300
paper reading - Tree Transformer
de9uch1
0
270
Other Decks in Research
See All in Research
データサイエンティストをめぐる環境の違い2025年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
950
ペットのかわいい瞬間を撮影する オートシャッターAIアプリへの スマートラベリングの適用
mssmkmr
0
380
When Learned Data Structures Meet Computer Vision
matsui_528
1
4.2k
2026-01-30-MandSL-textbook-jp-cos-lod
yegusa
1
690
R&Dチームを起ち上げる
shibuiwilliam
1
200
衛星×エッジAI勉強会 衛星上におけるAI処理制約とそ取組について
satai
4
330
20年前に50代だった人たちの今
hysmrk
0
170
競合や要望に流されない─B2B SaaSでミニマム要件を決めるリアルな取り組み / Don't be swayed by competitors or requests - A real effort to determine minimum requirements for B2B SaaS
kaminashi
0
1k
Φ-Sat-2のAutoEncoderによる情報圧縮系論文
satai
3
140
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
780
第二言語習得研究における 明示的・暗示的知識の再検討:この分類は何に役に立つか,何に役に立たないか
tam07pb915
0
1.9k
IEEE AIxVR 2026 Keynote Talk: "Beyond Visibility: Understanding Scenes and Humans under Challenging Conditions with Diverse Sensing"
miso2024
0
130
Featured
See All Featured
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
Ten Tips & Tricks for a 🌱 transition
stuffmc
0
88
The browser strikes back
jonoalderson
0
800
The agentic SEO stack - context over prompts
schlessera
0
700
10 Git Anti Patterns You Should be Aware of
lemiorhan
PRO
659
61k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
220
DevOps and Value Stream Thinking: Enabling flow, efficiency and business value
helenjbeal
1
150
How to Align SEO within the Product Triangle To Get Buy-In & Support - #RIMC
aleyda
1
1.4k
Color Theory Basics | Prateek | Gurzu
gurzu
0
250
Joys of Absence: A Defence of Solitary Play
codingconduct
1
310
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3.1k
From π to Pie charts
rasagy
0
150
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶