The LDA Topic Model Extension Study

DOI

10.2991/lemcs-15.2015.169How to use a DOI?

Keywords

LDA; Text Retrieval; Semantics Mining; Topic Model; Document Generation

Abstract

This article is a literature review that introduces the status quo of research on the LDA in recent years. The topic model of LDA[1] (Latent Dirichlet Allocation) was proposed by D.M. Blei in 2003, which obtained three Bayesian probability model on the extension of the probability of latent indexing (probabilistic Latent Semantic Indexing, pLSI ). It consists of the documents, topics and words, which mining implicit subject of the statistical probability model from a semantic document by modeling. In this article, researchers briefly introduce the LDA topic model and the documents generation process, but also introduce several the extended model based on LDA that has a mainstream representative part and advancement, sum up the research methods of extension of the study based on LDA, show the results in the field of study, and give personal suggestions to the future study of topic model based on LDA.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Qingquan Yang
AU  - Weijiang Li
PY  - 2015/07
DA  - 2015/07
TI  - The LDA Topic Model Extension Study
BT  - Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science
PB  - Atlantis Press
SP  - 857
EP  - 860
SN  - 1951-6851
UR  - https://doi.org/10.2991/lemcs-15.2015.169
DO  - 10.2991/lemcs-15.2015.169
ID  - Yang2015/07
ER  -