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
140
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
590
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
290
20240226_AAMT-Japio
de9uch1
0
160
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
130
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
180
My Research Environmental Setup
de9uch1
0
300
Nearest Neighbor Machine Translation
de9uch1
0
260
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
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
0
210
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
230
Combinatorial Search with Generators
kei18
0
1.1k
カスタマーサクセスの視点からAWS Summitの展示を考える~製品開発で活用できる勘所~
masakiokuda
2
210
20250624_熊本経済同友会6月例会講演
trafficbrain
1
730
PhD Defense 2025: Visual Understanding of Human Hands in Interactions
tkhkaeio
1
270
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
920
Unsupervised Domain Adaptation Architecture Search with Self-Training for Land Cover Mapping
satai
3
250
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
840
電通総研の生成AI・エージェントの取り組みエンジニアリング業務向けAI活用事例紹介
isidaitc
1
1.1k
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
280
多言語カスタマーインタビューの“壁”を越える~PMと生成AIの共創~ 株式会社ジグザグ 松野 亘
watarumatsuno
0
140
Featured
See All Featured
Building an army of robots
kneath
306
46k
Writing Fast Ruby
sferik
630
62k
We Have a Design System, Now What?
morganepeng
53
7.9k
Designing for Performance
lara
610
69k
Learning to Love Humans: Emotional Interface Design
aarron
274
41k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
132
19k
Six Lessons from altMBA
skipperchong
29
4k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
359
30k
The Power of CSS Pseudo Elements
geoffreycrofte
80
6k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
What’s in a name? Adding method to the madness
productmarketing
PRO
24
3.7k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
190
55k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶