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
結合トピックモデル
Search
Kento Nozawa
March 29, 2016
Research
0
1.1k
結合トピックモデル
2016年3月29日に『トピックモデルによる統計的潜在意味解析』
読書会ファイナル ~佐藤一誠先生スペシャル~のLTで発表しました
Kento Nozawa
March 29, 2016
Tweet
Share
More Decks by Kento Nozawa
See All by Kento Nozawa
Analysis on Negative Sample Size in Contrastive Unsupervised Representation Learning
nzw0301
0
170
[IJCAI-ECAI 2022] Evaluation Methods for Representation Learning: A Survey
nzw0301
0
610
[NeurIPS Japan meetup 2021 talk] Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
nzw0301
0
200
[IBIS2021] 対照的自己教師付き表現学習おける負例数の解析
nzw0301
0
180
Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
nzw0301
0
490
Introduction of PAC-Bayes and its Application for Contrastive Unsupervised Representation Learning
nzw0301
2
820
NLP Tutorial; word representation learning
nzw0301
0
220
Analyzing Centralities of Embedded Nodes
nzw0301
0
170
Paper Reading: Noise-Contrastive Estimation of Unnormalized Statistical Models, with Applications to Natural Image Statistics
nzw0301
2
1.2k
Other Decks in Research
See All in Research
とあるSREの博士「過程」 / A Certain SRE’s Ph.D. Journey
yuukit
10
4.2k
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
kurita
0
170
EOGS: Gaussian Splatting for Efficient Satellite Image Photogrammetry
satai
4
500
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
180
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
masakat0
0
110
cvpaper.challenge 10年の軌跡 / cvpaper.challenge a decade-long journey
gatheluck
3
310
Agentic AIとMCPを利用したサービス作成入門
mickey_kubo
0
520
利用シーンを意識した推薦システム〜SpotifyとAmazonの事例から〜
kuri8ive
1
240
言語モデルの地図:確率分布と情報幾何による類似性の可視化
shimosan
5
1.4k
投資戦略202508
pw
0
550
Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets
satai
3
260
[論文紹介] Intuitive Fine-Tuning
ryou0634
0
110
Featured
See All Featured
Building Applications with DynamoDB
mza
96
6.6k
Designing for Performance
lara
610
69k
Build your cross-platform service in a week with App Engine
jlugia
231
18k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
44
2.5k
Art, The Web, and Tiny UX
lynnandtonic
302
21k
Java REST API Framework Comparison - PWX 2021
mraible
33
8.8k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
Docker and Python
trallard
45
3.5k
Raft: Consensus for Rubyists
vanstee
140
7.1k
It's Worth the Effort
3n
187
28k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Transcript
݁߹τϐοΫϞσϧ ʰτϐοΫϞσϧʹΑΔ౷ܭతજࡏҙຯղੳʱ ಡॻձϑΝΠφϧ ~ࠤ౻Ұઌੜεϖγϟϧ~ ݈ਓ (@nzw0301) 2016-03-29
ࣗݾհ ͡Ί·ͯ͠ ݈ਓ (@nzw0301) य़͔ΒஜେͰM1 ڵຯ • ػցֶशɼNLPɼάϥϑɼDL
݁߹τϐοΫϞσϧ จॻσʔλͱରԠ͢ΔใΛ߹Θֶͤͯश • ຊޠͱӳޠ • Ϩγϐͱࡐྉ • ୯ޠͱͦͷࢺ ࢀߟɿ௨ৗͷLDAͷάϥϑΟΧϧϞσϧ 3
D N2 N1 K 2 1 w2 i w1 i ✓ ↵ 1 z1 i z2 i 2 D N K wi ✓ ↵ zi
z ͷαϯϓϦϯάࣜ • 3ষp55ʹैͬͯಋग़Մೳ • ৄ͘͠ http://nzw0301.github.io/2016/02/jointTopicModelsEquation • ҎԼͷ͔ࣜΒGibbs SamplingͷࣜΛٻΊΔ
ࢀߟɿ௨ৗͷLDA 4 p(z1 d,i = k|w1 d,i = v, W1 \d,i , W2, Z1 \d,i , Z2, ↵, 1, 2) p(z1 d,i = k|w1 d,i = v, W1 \d,i , Z1 \d,i , ↵, 1)
ࣜมܗͷ݁Ռ • ݁߹τϐοΫϞσϧͷαϯϓϦϯάࣜ • φ௨ৗͷLDAͱಉ͡ • θʹ͍ͭͯɼؚ·ΕΔ߲͕ิॿใͷ͚ͩ૿͑Δ ࢀߟɿ௨ৗͷLDAͷαϯϓϦϯάࣜ 5 n1
k,v,\d,i + v P v0 (n1 k,v0,\d,i + v0 ) n1 d,k,\d,i + n2 d,k + ↵k P k0 (n1 d,k0,\d,i + n2 d,k0 + ↵k0 ) n1 k,v,\d,i + v P v0 (n1 k,v0,\d,i + v0 ) n1 d,k,\d,i + ↵k P k0 (n1 d,k0,\d,i + ↵k0 )
࣮ߦྫ • ର༁ίʔύεΛఆͨ͠؆୯ͳྫ • ݴޠ͕ҧͬͯτϐοΫڞ௨ http://nzw0301.github.io/2016/02/jointTopicModelsEquation ࣮ɿLDAͷαϯϓϧࣜͰ͏౷ܭྔΛྻʹ 6
ࢀߟจݙ • ؠా ۩࣏. τϐοΫϞσϧ. ߨஊࣾ. 2015. (MLPػցֶशϓϩϑΣογϣφϧγϦʔζ). • ࠤ౻
Ұ. τϐοΫϞσϧʹΑΔ౷ܭతજࡏҙຯղੳ. ίϩφࣾ. 2015. (ࣗવݴޠॲཧγ Ϧʔζ, 8). • David Mimno, Hanna M. Wallach, Jason Naradowsky, David A. Smith and Andrew McCallum. 2009. Polylingual Topic Models. in EMNLP. 7