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
0
51
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
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
120
20240226_AAMT-Japio
de9uch1
0
80
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
97
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
120
My Research Environmental Setup
de9uch1
0
220
Nearest Neighbor Machine Translation
de9uch1
0
190
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
230
paper reading - Tree Transformer
de9uch1
0
190
Dependency-Based Self-Attention for Transformer NMT (RANLP2019)
de9uch1
0
53
Other Decks in Research
See All in Research
大規模言語モデルのバイアス
yukinobaba
PRO
4
700
Generative Predictive Model for Autonomous Driving 第61回 コンピュータビジョン勉強会@関東 (後編)
kentosasaki
0
210
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
eumesy
PRO
7
1.2k
Weekly AI Agents News! 9月号 プロダクト/ニュースのアーカイブ
masatoto
2
140
医療支援AI開発における臨床と情報学の連携を円滑に進めるために
moda0
0
110
EBPMにおける生成AI活用について
daimoriwaki
0
180
非ガウス性と非線形性に基づく統計的因果探索
sshimizu2006
0
360
ニューラルネットワークの損失地形
joisino
PRO
35
16k
大規模言語モデルを用いた日本語視覚言語モデルの評価方法とベースラインモデルの提案 【MIRU 2024】
kentosasaki
2
520
Kaggle役立ちアイテム紹介(入門編)
k951286
14
4.6k
「並列化時代の乱数生成」
abap34
3
820
第79回 産総研人工知能セミナー 発表資料
agiats
2
160
Featured
See All Featured
The Art of Programming - Codeland 2020
erikaheidi
52
13k
Making Projects Easy
brettharned
115
5.9k
Rails Girls Zürich Keynote
gr2m
94
13k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
356
29k
How To Stay Up To Date on Web Technology
chriscoyier
788
250k
Building a Modern Day E-commerce SEO Strategy
aleyda
38
6.9k
Speed Design
sergeychernyshev
24
610
RailsConf 2023
tenderlove
29
900
Bootstrapping a Software Product
garrettdimon
PRO
305
110k
Building Better People: How to give real-time feedback that sticks.
wjessup
364
19k
Build The Right Thing And Hit Your Dates
maggiecrowley
33
2.4k
No one is an island. Learnings from fostering a developers community.
thoeni
19
3k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶