Upgrade to Pro — share decks privately, control downloads, hide ads and more …

文献紹介 10月3日

gumigumi7
October 03, 2018
320

文献紹介 10月3日

Gaussian LDA for Topic Models with Word Embeddings

gumigumi7

October 03, 2018
Tweet

Transcript

  1.  ▪  ▪ Rajarshi Das, Manzil Zaheer, Chris Dyer.

    ▪ Gaussian LDA for Topic Models with Word Embeddings. ▪ Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pages 795– 804. 2015. ▪  ▪ LDA, Word2Vec 2
  2.  ▪ ML V P e W WV Lr A

    ▪ o 2 I D V L 3
  3.  ▪ LDA (Latent Dirichlet Allocation) ▪ '#%)  ,(-

    ▪   )+&$ )+&$  ,(- ! "# $#,& '#,& () *     d     d n   d n k    
  4.  ▪ LDA (Latent Dirichlet Allocation) ▪ '#%)  ,(-

    ▪   )+&$ )+&$  ,(-
  5.  ▪ Gaussian LDA ▪   ▪  

     ! "# $#,& '#,& () , Σ) (, +, ,, -     d     d n   d n   k    
  6.  ▪ Wikipedia*PMI0$ ▪ 6843*&PMI0 # #$ & ▪ 

    !"/,!-( ) . ▪ Word2Vec+Wikipedia*& ▪ 684395:+20-NEWSGROUP'NIPS0