Lock in $30 Savings on PRO—Offer Ends Soon! ⏳
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
150
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
620
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
300
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
140
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
190
My Research Environmental Setup
de9uch1
0
310
Nearest Neighbor Machine Translation
de9uch1
0
270
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
290
paper reading - Tree Transformer
de9uch1
0
260
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
330
Remote sensing × Multi-modal meta survey
satai
4
650
J-RAGBench: 日本語RAGにおける Generator評価ベンチマークの構築
koki_itai
0
1.1k
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
130
論文読み会 SNLP2025 Learning Dynamics of LLM Finetuning. In: ICLR 2025
s_mizuki_nlp
0
350
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
65
35k
Panopticon: Advancing Any-Sensor Foundation Models for Earth Observation
satai
3
460
若手研究者が国際会議(例えばIROS)でワークショップを企画するメリットと成功法!
tanichu
0
130
さまざまなAgent FrameworkとAIエージェントの評価
ymd65536
1
370
湯村研究室の紹介2025 / yumulab2025
yumulab
0
270
AIスパコン「さくらONE」の オブザーバビリティ / Observability for AI Supercomputer SAKURAONE
yuukit
2
1k
When Learned Data Structures Meet Computer Vision
matsui_528
1
1.6k
Featured
See All Featured
The SEO Collaboration Effect
kristinabergwall1
0
310
How to Build an AI Search Optimization Roadmap - Criteria and Steps to Take #SEOIRL
aleyda
1
1.8k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.4k
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
27
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
Done Done
chrislema
186
16k
How to build an LLM SEO readiness audit: a practical framework
nmsamuel
1
580
Information Architects: The Missing Link in Design Systems
soysaucechin
0
710
Bash Introduction
62gerente
615
210k
Building Flexible Design Systems
yeseniaperezcruz
330
39k
We Analyzed 250 Million AI Search Results: Here's What I Found
joshbly
0
250
Color Theory Basics | Prateek | Gurzu
gurzu
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶