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
300
paper reading - Tree Transformer
de9uch1
0
270
Other Decks in Research
See All in Research
老舗ものづくり企業でリサーチが変革を起こすまで - 三菱重工DXの実践
skydats
0
150
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
490
英語教育 “研究” のあり方:学術知とアウトリーチの緊張関係
terasawat
1
960
Any-Optical-Model: A Universal Foundation Model for Optical Remote Sensing
satai
3
700
Φ-Sat-2のAutoEncoderによる情報圧縮系論文
satai
4
640
LINEヤフー データサイエンス Meetup「三井物産コモディティ予測チャレンジ」の舞台裏-AlpacaTechパート
gamella
1
500
「AIとWhyを深堀る」をAIと深堀る
iflection
0
390
通時的な類似度行列に基づく単語の意味変化の分析
rudorudo11
0
280
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
shunk031
4
930
コーディングエージェントとABNを再考
hf149
2
610
はじまりの クエスチョンブック —余暇と豊かさにあふれた社会とは?
culturaltransition
PRO
0
440
進学校の生徒にはア行の苗字が多いのか
ozekinote
0
400
Featured
See All Featured
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
23k
Organizational Design Perspectives: An Ontology of Organizational Design Elements
kimpetersen
PRO
1
700
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
340
The Limits of Empathy - UXLibs8
cassininazir
1
330
Java REST API Framework Comparison - PWX 2021
mraible
34
9.3k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
38
2.9k
Skip the Path - Find Your Career Trail
mkilby
1
120
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.6k
ラッコキーワード サービス紹介資料
rakko
1
3.3M
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4k
Unlocking the hidden potential of vector embeddings in international SEO
frankvandijk
0
800
A Soul's Torment
seathinner
6
2.8k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶