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
100
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
370
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
220
20240226_AAMT-Japio
de9uch1
0
130
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
120
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
160
My Research Environmental Setup
de9uch1
0
270
Nearest Neighbor Machine Translation
de9uch1
0
230
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
270
paper reading - Tree Transformer
de9uch1
0
230
Other Decks in Research
See All in Research
Self-supervised audiovisual representation learning for remote sensing data
satai
3
130
Scale-Aware Recognition in Satellite images Under Resource Constraints
satai
3
180
Weekly AI Agents News!
masatoto
33
64k
Weekly AI Agents News! 12月号 論文のアーカイブ
masatoto
0
290
NLP2025 WS Shared Task 文法誤り訂正部門 ehiMetrick
sugiyamaseiji
0
170
3D Gaussian Splattingによる高効率な新規視点合成技術とその応用
muskie82
0
560
[輪講] Transformer Layers as Painters
nk35jk
4
760
DeepSeek を利用する上でのリスクと安全性の考え方
schroneko
3
1.4k
サーブレシーブ成功率は勝敗に影響するか?
vball_panda
0
640
Sosiaalisen median katsaus 03/2025 + tekoäly
hponka
0
870
GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
satai
3
130
SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
satai
3
130
Featured
See All Featured
Raft: Consensus for Rubyists
vanstee
137
6.9k
Building Adaptive Systems
keathley
41
2.5k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
34
2.2k
How to Think Like a Performance Engineer
csswizardry
23
1.6k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.7k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
41
2.3k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
49k
We Have a Design System, Now What?
morganepeng
52
7.5k
GraphQLとの向き合い方2022年版
quramy
46
14k
Optimizing for Happiness
mojombo
378
70k
What's in a price? How to price your products and services
michaelherold
245
12k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
129
19k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶