id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_4edup4wwozbhdb2gbpd24ungsu	Dat Quoc Nguyen	Improving Topic Models with Latent Feature Word Representations	2015	29	.pdf	application/pdf	3167	520	81	Improving Topic Models with Latent Feature Word Representations • Topic models take a corpus of documents as input, and jointly cluster: corpus to improve the topic-word distributions in a topic model Latent-feature topic-to-word distributions • In our topic models, we mix the CatE distribution with a multinomial initialise the word-topic variables zdi using the LDA sampler initialise the word-topic variables zdi using the DMM sampler • A topic model learns document-topic and topic-word distributions: • Do the word2vec and Glove word vectors behave differently in topic 20-topic word2vec-DMM on the TMN titles corpus 20-topic word2vec-DMM on the TMN titles corpus Evaluation of 20-topic LDA on the N20 short corpus, • For document classification the latent feature models generally perform corpus to accurately estimate topic-word distributions • More sophisticated latent-feature models of topic-word distributions Conclusions and future work Conclusions and future work Conclusions and future work Conclusions and future work Conclusions and future work	./cache/work_4edup4wwozbhdb2gbpd24ungsu.pdf	./txt/work_4edup4wwozbhdb2gbpd24ungsu.txt