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
170
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
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
770
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
350
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
340
Nearest Neighbor Machine Translation
de9uch1
0
280
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
310
paper reading - Tree Transformer
de9uch1
0
280
Other Decks in Research
See All in Research
「AIとWhyを深堀る」をAIと深堀る
iflection
0
470
オーストリア流 都市の公共交通サービス水準評価@公共交通オープンデータ最前線2026
trafficbrain
0
180
第12回人と環境にやさしい交通をめざす全国大会/熊本都市圏「車1割削減、渋滞半減、公共交通2倍」をめざして
trafficbrain
0
110
言語モデルから言語について語る際に押さえておきたいこと
eumesy
PRO
5
2.3k
ペットのかわいい瞬間を撮影する オートシャッターAIアプリへの スマートラベリングの適用
mssmkmr
0
510
東京大学工学部計数工学科、計数工学特別講義の説明資料
kikuzo
0
460
Ghost in the 7‑Zip: The Shadow of Residential Proxies Creeping into Your Life
nttcom
0
950
2026年3月1日(日)福島「除染土」の公共利用をかんがえる
atsukomasano2026
0
620
量子コンピュータの紹介
oqtopus
0
320
Unified Audio Source Separation (Defense Slides)
kohei_1979
1
610
The mathematics of transformers
gpeyre
0
310
都市交通マスタープランとその後への期待@熊本商工会議所・熊本経済同友会
trafficbrain
0
220
Featured
See All Featured
More Than Pixels: Becoming A User Experience Designer
marktimemedia
3
430
Embracing the Ebb and Flow
colly
88
5.1k
A better future with KSS
kneath
240
18k
The Organizational Zoo: Understanding Human Behavior Agility Through Metaphoric Constructive Conversations (based on the works of Arthur Shelley, Ph.D)
kimpetersen
PRO
0
360
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.8k
State of Search Keynote: SEO is Dead Long Live SEO
ryanjones
0
200
The Spectacular Lies of Maps
axbom
PRO
1
790
[SF Ruby Conf 2025] Rails X
palkan
2
1.1k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
3.4k
Joys of Absence: A Defence of Solitary Play
codingconduct
1
390
Become a Pro
speakerdeck
PRO
31
6k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶