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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Hiroyuki Deguchi
March 22, 2024
Research
170
0
Share
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
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
750
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
340
20240226_AAMT-Japio
de9uch1
0
190
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
330
Nearest Neighbor Machine Translation
de9uch1
0
280
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
310
paper reading - Tree Transformer
de9uch1
0
280
Other Decks in Research
See All in Research
2026年3月1日(日)福島「除染土」の公共利用をかんがえる
atsukomasano2026
0
600
正規分布と最適化について
koide3
0
200
非試合日の野球場を楽しむためのARホームランボールキャッチ体験システムの開発 / EC79-miyazaki
yumulab
0
180
2026 東京科学大 情報通信系 研究室紹介 (すずかけ台)
icttitech
0
3.5k
AIエージェント時代のLLM-jpモデルのあるべき姿
k141303
0
380
Harness Engineering and Al Agent
kzinmr
3
1.4k
LLM Compute Infrastructure Overview
karakurist
2
1.3k
LLMアプリケーションの透明性について
fufufukakaka
0
220
Dual Quadric表現を用いた動的物体追跡とRGB-D・IMU制約の密結合によるオドメトリ推定
nanoshimarobot
0
370
重要だけど測れていないもの:高齢者ケアの見えない課題
theoriatec2024
0
280
Research Engineerという仕事 / Research Engineering: Bridging Research and Business
chck
1
130
都市交通マスタープランとその後への期待@熊本商工会議所・熊本経済同友会
trafficbrain
0
210
Featured
See All Featured
How GitHub (no longer) Works
holman
316
150k
Measuring Dark Social's Impact On Conversion and Attribution
stephenakadiri
2
200
Darren the Foodie - Storyboard
khoart
PRO
3
3.3k
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
810
Designing Experiences People Love
moore
143
24k
[SF Ruby Conf 2025] Rails X
palkan
2
1k
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
techseoconnect
PRO
0
140
KATA
mclloyd
PRO
35
15k
Side Projects
sachag
455
43k
Building Experiences: Design Systems, User Experience, and Full Site Editing
marktimemedia
0
510
Heart Work Chapter 1 - Part 1
lfama
PRO
7
36k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶