Upgrade to Pro — share decks privately, control downloads, hide ads and more …
Sign up for free

Ensemble Topic Modelling

Avatar for Leland McInnes Leland McInnes
July 12, 2019
Research
500
1

Ensemble Topic Modelling

A short lightning talk on ensemble topic modelling with pLSA using the enstop package.

Avatar for Leland McInnes

Leland McInnes

July 12, 2019

More Decks by Leland McInnes

See All by Leland McInnes
PyNNDescent: Fast Approximate Nearest Neighbors with Numba
Avatar for Leland McInnes lmcinnes
0
1.1k
Word and Document Embeddings
Avatar for Leland McInnes lmcinnes
0
180
Topological Data Analysis
Avatar for Leland McInnes lmcinnes
1
380
Learning Topology: topological methods for unsupervised learning
Avatar for Leland McInnes lmcinnes
2
3.7k
A Guide to Dimension Reduction
Avatar for Leland McInnes lmcinnes
3
1.5k
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
Avatar for Leland McInnes lmcinnes
2
2.8k

Other Decks in Research

See All in Research
ros2-perf-multihost: 分散システムにおける客観的なアーキテクチャ評価フレームワーク
Avatar for takasehideki takasehideki
0
280
2025年度秋葉原ウォーカブルプロジェクト調査報告 「アキバらしいウォーカブル」とは何か
Avatar for 日本大学 都市計画研究室（泉山ゼミ） izumiyama_lab
1
240
[最先端NLP勉強会2026] Agentic Rubrics as Contextual Verifiers for SWE Agents
Avatar for Ryo Fujii rfujii
1
380
[IR Reading 2026春 論文紹介] LLM-based Listwise Reranking under the Effect of Positional Bias (ECIR 2026) /IR-Reading-2026-Spring
Avatar for Kohei Shinden koheishinden
PRO
0
460
ふとした出会いで生まれたSkillが、 社内利用1位になるまで
Avatar for earlgrayMK mikimhk
22
24k
大規模言語モデルは誰を覚えているか / Who Do Large Language Models Memorize?
Avatar for Shotaro Ishihara upura
0
210
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
Avatar for Hiroyuki Deguchi de9uch1
2
290
ros2-perf-multihost: Automated Coordination Framework for Objective Architecture Evaluation in Distributed Systems
Avatar for takasehideki takasehideki
0
130
Développer des solutions de réduction des émissions de méthane entérique : 1ers résultats Méthane 2030
Avatar for Idele institutdelelevage
PRO
0
230
PHTalks Bengaluru - SSRF When All Else Fails
Avatar for Debangshu Kundu dk999
0
1.2k
[最先端NLP勉強会2026] Checklists Are Better Than Reward Models For Aligning Language Models
Avatar for Kento Nozawa nzw0301
1
330
人間中心の意思決定支援AI
Avatar for Yukino Baba yukinobaba
PRO
7
4.2k

Featured

See All Featured
Conquering PDFs: document understanding beyond plain text
Avatar for Ines Montani inesmontani
PRO
4
3.2k
Practical Tips for Bootstrapping Information Extraction Pipelines
Avatar for Matthew Honnibal honnibal
25
2.1k
Designing Dashboards & Data Visualisations in Web Apps
Avatar for Des Traynor destraynor
232
55k
Effective software design: The role of men in debugging patriarchy in IT @ Voxxed Days AMS
Avatar for Kenny Baas-Schwegler baasie
1
550
Beyond borders and beyond the search box: How to win the global "messy middle" with AI-driven SEO
Avatar for David Carrasco davidcarrasco
3
270
RailsConf 2023
Avatar for Aaron Patterson tenderlove
30
1.6k
The SEO identity crisis: Don't let AI make you average
Avatar for Varn varn
0
580
Discover your Explorer Soul
Avatar for Emna emna__ayadi
2
1.3k
Mobile First: as difficult as doing things right
Avatar for Swwweet swwweet
225
10k
Fashionably flexible responsive web design (full day workshop)
Avatar for Andy Clarke malarkey
409
67k
The Power of CSS Pseudo Elements
Avatar for Geoffrey Crofte geoffreycrofte
82
6.6k
How to Think Like a Performance Engineer
Avatar for Harry Roberts csswizardry
28
2.9k

Transcript

  1. Ensemble Topic Modelling Leland McInnes

  2. Model a corpus of documents in terms of underlying “topics”

  3. Topic Modelling as Matrix Factorization

  4. None
  5. None
  6. None
  7. None

  8. LDA and pLSA are probabilistic matrix factorization methods

  9. (Ensembles of) pLSA

  10. Performance?

  11. None

  12. Quality?

  13. None

  14. Instability?

  15. These are hard optimization problems

  16. Topics vary from one run to another

  17. What are the stable topics? Inspired by https://github.com/RaRe-Technologies/gensim/pull/2282

  18. None

  19. Each cluster represents a stable topic

  20. None

  21. • Greater stability • Determines number of topics automatically •

    Embarrassingly parallel computation

  22. Implementation

  23. sklearn API

  24. None

  25. https://github.com/lmcinnes/enstop

  26. pip install enstop