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
Hiroyuki Deguchi
March 22, 2024
Research
180
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
20260427-EhimeDSCSeminar-MBR-CBDT-Decoding
de9uch1
1
12
260624_NLP-colloquium: Hubness
de9uch1
2
210
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
1
830
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
370
20240226_AAMT-Japio
de9uch1
0
210
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
180
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
240
My Research Environmental Setup
de9uch1
0
350
Nearest Neighbor Machine Translation
de9uch1
0
300
Other Decks in Research
See All in Research
typst の使い方:言語学を研究する学生のために
gitomochang
0
570
Cross-Media Information Spaces and Architectures
signer
PRO
0
360
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
650
2025年度秋葉原ウォーカブルプロジェクト調査報告 「アキバらしいウォーカブル」とは何か
izumiyama_lab
1
200
研究室単位での自律的 IPv6接続性確立に向けたAS共同運用モデルの提案と実証
reokashiwa
PRO
0
210
JICA QUEST 共創×革新プログラム Impact Report(海ノ向こうコーヒー)
ontheslope
0
500
Anthropic が提案する LLM の内部状態を自然言語で説明可能にした Natural Language Autoencoders / Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activations
shunk031
0
200
SoftMatcha 2: 1兆語規模コーパスの超高速かつ柔らかい検索
e869120_sub
7
3.8k
長時間動画QAにおけるマルチエージェント推論 ・SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
murakawatakuya
1
200
セマンティック通信勉強会 6Gに向けたデバイス間効率的な通信の技術紹介・課題・今後展望
satai
3
310
大規模言語モデルは誰を覚えているか / Who Do Large Language Models Memorize?
upura
0
150
PGDM: Physically Guided Diffusion Model for L Downscaling
satai
3
450
Featured
See All Featured
Darren the Foodie - Storyboard
khoart
PRO
3
3.8k
Utilizing Notion as your number one productivity tool
mfonobong
4
560
Facilitating Awesome Meetings
lara
57
7.1k
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4.1k
16th Malabo Montpellier Forum Presentation
akademiya2063
PRO
0
370
Learning to Love Humans: Emotional Interface Design
aarron
275
41k
The Director’s Chair: Orchestrating AI for Truly Effective Learning
tmiket
1
290
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
201
75k
Getting science done with accelerated Python computing platforms
jacobtomlinson
2
460
Have SEOs Ruined the Internet? - User Awareness of SEO in 2025
akashhashmi
0
460
Mobile First: as difficult as doing things right
swwweet
225
10k
How to optimise 3,500 product descriptions for ecommerce in one day using ChatGPT
katarinadahlin
PRO
2
3.8k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶