Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
20250226 NLP colloquium: "SoftMatcha: 10億単語規模コー...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Hiroyuki Deguchi
February 26, 2025
Research
840
1
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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"
Hiroyuki Deguchi
February 26, 2025
More Decks by Hiroyuki Deguchi
See All by Hiroyuki Deguchi
20260427 Ehime DS Seminar: MBR-CBDT Decoding
de9uch1
1
38
20260624 NLP colloquium: 単一のhubテキストがCLIPを壊す:hubnessによる埋め込みの脆弱性特定
de9uch1
2
280
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
380
サブセット探索を用いた高速なkNNニューラル機械翻訳
de9uch1
0
180
20240226_AAMT-Japio
de9uch1
0
210
Searching for Needles in a Haystack: On the Role of Incidental Bilingualism in PaLM’s Translation Capability
de9uch1
0
180
Paper Reading: Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation
de9uch1
0
240
My Research Environmental Setup
de9uch1
0
350
Nearest Neighbor Machine Translation
de9uch1
0
300
Other Decks in Research
See All in Research
【ローカルAIに向き合う展示会vol.2】液体時間定数型モジュールを用いた オリジナルの双方向エンコーダーモデルNexteraBERT 推論速度向上検討並びにダウンストリーム評価
rikkabotan7
0
200
クラウド・AI 時代の研究開発 DX / R&D Digital Transformation
hariby
0
140
Vector Map as Language: Toward Unified Remote Sensing Vector Mapping
satai
3
280
Research Engineerという仕事 / Research Engineering: Bridging Research and Business
chck
1
350
LLM の Attention 機構まとめ — 数式・計算量・メモリ
puwaer
8
2.7k
[SNLP2026] Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
wataruuuuu
0
320
Spatial Active Noise Control Based onSound Field Interpolation Incorporating Physical Constraints
skoyamalab
0
190
視覚若手の会LENSって何??
mickey_0226
0
250
COMETAを用いたデータ民主化運動の歴史
sazimai
0
250
Harness Engineering and Al Agent
kzinmr
3
2k
量子サマースクール2026「量子計算機アーキテクチャ分野の概観」
youten622
1
910
MM-OVSeg: Multimodal Optical–SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing
satai
3
130
Featured
See All Featured
Technical Leadership for Architectural Decision Making
baasie
3
570
The Curious Case for Waylosing
cassininazir
1
520
[SF Ruby Conf 2025] Rails X
palkan
3
1.4k
Navigating the moral maze — ethical principles for Al-driven product design
skipperchong
2
550
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.8k
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
minecr
1
400
Neural Spatial Audio Processing for Sound Field Analysis and Control
skoyamalab
0
510
Stop Working from a Prison Cell
hatefulcrawdad
274
21k
Product Roadmaps are Hard
iamctodd
55
13k
Measuring Dark Social's Impact On Conversion and Attribution
stephenakadiri
2
280
Designing Powerful Visuals for Engaging Learning
tmiket
1
570
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Transcript
None
◼ ⚫ ⚫ ⚫ ⚫ ⚫ ◼ ⚫ ⚫ ⚫
◼ ◼ ◼ ◼
◼ ◼ ◼ ◼
◼ ◼ ◼ ◼
𝑤 ◼ 𝑤 ◼ ⚫ 𝑤 ⚫ 𝑤 ◼ ⚫
◼ ⚫ ◼ ⚫ ◼ ⚫ (Radovanovic+, JMLR2010) ⚫ ▶
Wang+, (arxiv) 2022, “Text Embeddings by Weakly-Supervised Contrastive Pre-training”. Radovanovic+, JMLR 2010, “Hubs in space: Popular nearest neighbors in high-dimensional data”.
◼ ◼ ◼ ◼
◼ ⚫ 𝐩 = 𝑝1 , … , 𝑝𝑀 ∈
Σ∗ ⚫ 𝐭 = 𝑡1 , … , 𝑡𝑁 ∈ Σ∗ ▶ Σ∗ ◼ ⚫ ⚫ ◼ ◼
◼ ⚫ 𝑤 ∈ 𝒱 𝐷 ⚫ 𝐯𝑤 ∈ ℝ𝐷
≔ 𝑤 ⚫ ▶ cos 𝐯person , 𝐯people > cos 𝐯person , 𝐯bird ▶
◼ ◼ ⚫ ※
◼ ⚫ 𝑡𝑖 = 𝑝𝑗 cos 𝐯𝑡𝑖 , 𝐯𝑝𝑗 ≥
𝛼 ▶ 𝛼 = 1.0 ※ 𝛼 = 0.7 ◼ ⚫ ⚫
𝑡1 𝑡2 𝑡3 𝑡4 𝑡5 𝑡6 𝑡7 𝑡8 𝑡9 𝑡10
𝑡11 𝑡12 𝑡13 ◼ ◼ ◼ ⚫
◼ 𝒮𝑤 ≔ 𝑣 ∈ 𝒱 cos 𝐯𝑣 ⊤𝐯𝑤 ≥
𝛼 ⚫ 𝑤 𝒮we 𝒮talk 𝒮about
⇔ 𝒮we , 𝒮talk , 𝒮about ⇔ 𝒮we , 𝒮talk
, 𝒮about 𝑖, 𝑖 + 1, 𝑖 + 2 𝑖 𝒮we 𝒮talk 𝒮about
𝒮we 𝒮talk 𝒮about 𝒮we ℳ ℳ ← 1,10,6 𝒮talk ℳ
ℳ′ ← 2 − 1, 11 − 1,7 − 1 = 1,10,6 ℳ ← ℳ ∩ ℳ′ = 1,10,6 𝒮about ℳ ℳ′ ← 8 − 2, 12 − 2 = 6,10 ℳ ← ℳ ∩ ℳ′ = 6,10 ℳ
𝒮we 𝒮talk 𝒮about 𝑡1 𝑡2 𝑡3 𝑡4 𝑡5 𝑡6 𝑡7
𝑡8 𝑡9 𝑡10 𝑡11 𝑡12 𝑡13
𝒮𝑝1 𝐼𝒮𝑝1 𝒮𝑝𝑀 𝐼𝒮𝑝𝑀 𝒮𝑝1 𝐼𝒮𝑝1 ℳ ℳ ← 𝐼𝒮𝑝1
𝑘 = 2, … , 𝑀 ℳ′ ← 𝑖 − 𝑘 + 1 𝑖 ∈ 𝐼𝒮𝑝𝑘 ℳ ← ℳ ∩ ℳ′ ℳ 𝐩 = 𝑝1 , … , 𝑝𝑀
◼ ⚫ ▶ ▶ ⚫
◼ ◼ ⚫ (Wang+, 2024) ⚫ (Douze+, 2024) (Malkov &
Yashunin, IEEE TPAMI, 2018) ◼ ⚫ ▶ 𝛼 = 0.55 (Pennington+, EMNLP2014) ▶ 𝛼 = 0.50 (Grave+, arXiv:1802.06893) Wang+, arXiv:2402.05672, “Multilingual E5 Text Embeddings: A Technical Report”. Douze+, arXiv:2401.08281, “The Faiss library”. Malkov & Yashunin, IEEE TPAMI, 2018, “Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs”. Pennington+, EMNLP2014, “GloVe: Global Vectors for Word Representation”. Grave+, arXiv:1802.06893, “Learning Word Vectors for 157 Languages”.
◼ ⚫ ▶ ⚫
◼ ⚫ ⚫ ◼ ⚫
◼ ⚫ (Crane, IJDL 2023) ⚫ (Bothwell+, EMNLP2023) ◼ Crane,
IJDL 2023, “The Perseus Digital Library and the future of libraries.”. Bothwell+, EMNLP2023, “Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines”.
◼ ⚫ ⚫ ⚫ ◼ ◼
◼ ⚫ ◼ ⚫ ▶ ◼ ⚫ ▶ ▶ ⚫
⚫
◼ ⚫ 𝐼𝒮𝑝𝑘 ▶ ⚫ ◼ ⚫
◼ ◼ ⚫ ⚫ ⚫ 𝑂 1 ▶ ◼ ⚫
⚫ ⚫ 𝑂 log |𝐵| ▶
◼ ⚫ ⚫ ◼ ⚫ ⚫ ▶ ⚫