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
16
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
20240226_AAMT-Japio
de9uch1
0
32
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
74
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
95
My Research Environmental Setup
de9uch1
0
190
Nearest Neighbor Machine Translation
de9uch1
0
160
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
210
paper reading - Tree Transformer
de9uch1
0
150
Dependency-Based Self-Attention for Transformer NMT (RANLP2019)
de9uch1
0
35
Other Decks in Research
See All in Research
CSC590 Lecture 01
javiergs
PRO
0
130
データで診て考える合志市の渋滞と公共交通 ~めざせ 車1割削減、渋滞半減、公共交通2倍~
trafficbrain
0
470
First Authorに俺はなるっ!! IROS’23 CCC2023 FY
shota_nishiyama
0
180
The Theory behind Vector DB
matsui_528
0
1.8k
Generative AI - practice and theory
gpeyre
1
580
Embodied AIについて / About Embodied AI
nttcom
1
570
My Journey as a UX Researcher
aranciap
0
1.1k
クロスモーダル表現学習の研究動向: 音声関連を中心として
ryomasumura
3
600
第14回対話システムシンポジウム EMNLP 2023 参加報告
atsumoto
0
160
AIを前提とした体験の実現に向けて/toward_ai_based_experiences
monochromegane
1
250
Equivalence of Geodesics and Importance Weighting from the Perspective of Information Geometry
mkimura
0
140
HP (Hitto Point: 筆頭ポイント)
tanichu
0
740
Featured
See All Featured
Designing with Data
zakiwarfel
96
4.8k
Ruby is Unlike a Banana
tanoku
96
10k
Java REST API Framework Comparison - PWX 2021
mraible
PRO
19
6.9k
Creating an realtime collaboration tool: Agile Flush - .NET Oxford
marcduiker
14
1.5k
Scaling GitHub
holman
457
140k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
323
20k
Statistics for Hackers
jakevdp
790
220k
StorybookのUI Testing Handbookを読んだ
zakiyama
13
4.6k
jQuery: Nuts, Bolts and Bling
dougneiner
59
7.1k
Fireside Chat
paigeccino
22
2.6k
Designing on Purpose - Digital PM Summit 2013
jponch
111
6.5k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
228
16k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶