Ensemble Topic Modelling

4c76f001e0a3d59cc5a269df70940dfd?s=47 Leland McInnes
July 12, 2019
Research
1
160

Ensemble Topic Modelling

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

4c76f001e0a3d59cc5a269df70940dfd?s=128

Leland McInnes

July 12, 2019
Tweet

More Decks by Leland McInnes

See All by Leland McInnes
4c76f001e0a3d59cc5a269df70940dfd?s=48 lmcinnes
1
51
4c76f001e0a3d59cc5a269df70940dfd?s=48 lmcinnes
2
2.7k
4c76f001e0a3d59cc5a269df70940dfd?s=48 lmcinnes
3
900
4c76f001e0a3d59cc5a269df70940dfd?s=48 lmcinnes
2
1.1k

Other Decks in Research

See All in Research
83722380372c00bd75ac920f2089f6aa?s=48 zacky1972
1
190
247ffe3c4d6ee344a081694419960a97?s=48 wangzwhu
0
220
A658ec7f1badf73819dfa501165016c1?s=48 yuukit
5
720
0fd69f775497ec247d1daff4ee7dcde8?s=48 yasuhiromuraji
1
220
951ca4f70b5884e18cf3f7e88c441d6a?s=48 issdu
0
1k
A54cce9a3933a049ca19477b7382cdde?s=48 agatan
1
270
E21d1f0881d623ba04709e94d75be2a8?s=48 tam17aki
2
1.1k
6bd63bb363d2cb9933b263463f6305cf?s=48 matsui_528
0
870
7d5c4656c947d0905dfbc5e39f233857?s=48 ayaniwa
8
2.3k
Bb6c3fc8c577710c72d03aeb4fa56bf6?s=48 masakat0
2
290
C33ee6184e05387228fd6283db8d6785?s=48 sportsai
0
170
A42dd3541cd40296dcd8a5e6b4a01bef?s=48 scatterlab
0
590

Featured

See All Featured
719435d98d452de7ac367c828266cf01?s=48 erikaheidi
5
3.5k
78b475797a14c84799063c7cd073962f?s=48 holman
287
130k
027d1ebf66cc039a0bd3b55eeadbe75d?s=48 sachag
266
16k
E190023b66e2b8aa73a842b106920c93?s=48 zenorocha
295
39k
Aebc2d07a50011e2a30d38435fde564a?s=48 jrom
113
6.8k
E4f5d494ebdc9e7cce1aecf3ce3e8bc1?s=48 shpigford
366
42k
3ab1249be442027903e1180025340b3f?s=48 reverentgeek
17
1.2k
C620790ae5bf5b50c245b2e0ef95f338?s=48 deanohume
293
27k
Eb8975af8e49e19e3dd6b6b84a542e26?s=48 qrush
282
18k
7559f6cff1f5efc2d210965febd4d71c?s=48 bermonpainter
340
25k
A60068bce2e73de3a37ca9d2dbe36092?s=48 bryan
100
11k
C9b18d9dff88a9dd2393364c2b3b21bd?s=48 colly
65
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