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
64
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
150
20240226_AAMT-Japio
de9uch1
0
89
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
100
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
130
My Research Environmental Setup
de9uch1
0
230
Nearest Neighbor Machine Translation
de9uch1
0
200
Paper Reading - Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation
de9uch1
0
240
paper reading - Tree Transformer
de9uch1
0
200
Dependency-Based Self-Attention for Transformer NMT (RANLP2019)
de9uch1
0
60
Other Decks in Research
See All in Research
さんかくのテスト.pdf
sankaku0724
0
550
12
0325
0
200
テキストマイニングことはじめー基本的な考え方からメディアディスコース研究への応用まで
langstat
1
150
LiDARとカメラのセンサーフュージョンによる点群からのノイズ除去
kentaitakura
0
200
移動ビッグデータに基づく地理情報の埋め込みベクトル化
tam1110
0
170
CoRL2024サーベイ
rpc
1
1.2k
精度を無視しない推薦多様化の評価指標
kuri8ive
1
290
Leveraging LLMs for Unsupervised Dense Retriever Ranking (SIGIR 2024)
kampersanda
2
260
EBPMにおける生成AI活用について
daimoriwaki
0
220
リモートワークにおけるパッシブ疲労
matsumoto_r
PRO
6
4.2k
大規模言語モデルのバイアス
yukinobaba
PRO
4
760
情報処理学会関西支部2024年度定期講演会「自然言語処理と大規模言語モデルの基礎」
ksudoh
10
2.2k
Featured
See All Featured
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
159
15k
Being A Developer After 40
akosma
87
590k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
32
2.7k
Large-scale JavaScript Application Architecture
addyosmani
510
110k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
17
2.3k
StorybookのUI Testing Handbookを読んだ
zakiyama
27
5.4k
Product Roadmaps are Hard
iamctodd
PRO
50
11k
KATA
mclloyd
29
14k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
26
1.5k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
2
290
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.6k
Scaling GitHub
holman
459
140k
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 ⚫ ⚫ ◼
⚫
⚫ ⚫ ▶ ⚫ ▶