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
160
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
730
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
340
20240226_AAMT-Japio
de9uch1
0
180
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
210
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
20年前に50代だった人たちの今
hysmrk
0
190
COFFEE-Japan PROJECT Impact Report(海ノ向こうコーヒー)
ontheslope
0
1.4k
Φ-Sat-2のAutoEncoderによる情報圧縮系論文
satai
4
470
CyberAgent AI Lab研修 / Social Implementation Anti-Patterns in AI Lab
chck
6
4.3k
「行ける・行けない表」による地域公共交通の性能評価
bansousha
0
140
正規分布と最適化について
koide3
0
130
typst の使い方:言語学を研究する学生のために
gitomochang
0
380
2026.01ウェビナー資料
elith
0
340
Sequences of Logits Reveal the Low Rank Structure of Language Models
sansantech
PRO
1
200
Aurora Serverless からAurora Serverless v2への課題と知見を論文から読み解く/Understanding the challenges and insights of moving from Aurora Serverless to Aurora Serverless v2 from a paper
bootjp
6
1.6k
LLM Compute Infrastructure Overview
karakurist
2
1.2k
YOLO26_ Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detection
satai
3
490
Featured
See All Featured
Pawsitive SEO: Lessons from My Dog (and Many Mistakes) on Thriving as a Consultant in the Age of AI
davidcarrasco
0
120
Building a Scalable Design System with Sketch
lauravandoore
463
34k
How to build a perfect <img>
jonoalderson
1
5.4k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
35
3.4k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.7k
Darren the Foodie - Storyboard
khoart
PRO
3
3.3k
SEO in 2025: How to Prepare for the Future of Search
ipullrank
3
3.4k
We Are The Robots
honzajavorek
0
220
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
5
820
What does AI have to do with Human Rights?
axbom
PRO
1
2.1k
How to audit for AI Accessibility on your Front & Back End
davetheseo
0
320
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶