$30 off During Our Annual Pro Sale. View Details »
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
610
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
地域丸ごとデイサービス「Go トレ」の紹介
smartfukushilab1
0
660
高畑鬼界ヶ島と重文・称名寺本薬師如来像の来歴を追って/kikaigashima
kochizufan
0
110
[論文紹介] Intuitive Fine-Tuning
ryou0634
0
160
Combining Deep Learning and Street View Imagery to Map Smallholder Crop Types
satai
3
300
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
fatemeh_fard
0
110
SREのためのテレメトリー技術の探究 / Telemetry for SRE
yuukit
13
2.6k
Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning
satai
2
150
Remote sensing × Multi-modal meta survey
satai
4
640
SNLP2025:Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
220
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
350
説明可能な機械学習と数理最適化
kelicht
2
750
長期・短期メモリを活用したエージェントの個別最適化
isidaitc
0
340
Featured
See All Featured
The Hidden Cost of Media on the Web [PixelPalooza 2025]
tammyeverts
2
120
Joys of Absence: A Defence of Solitary Play
codingconduct
1
250
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
57
37k
Why You Should Never Use an ORM
jnunemaker
PRO
61
9.6k
From π to Pie charts
rasagy
0
86
Test your architecture with Archunit
thirion
1
2.1k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
132
19k
Exploring anti-patterns in Rails
aemeredith
2
200
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
2.1k
Prompt Engineering for Job Search
mfonobong
0
120
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
31
3k
The untapped power of vector embeddings
frankvandijk
1
1.5k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶