Progressive EM for latent tree models and hierarchical topic detection

Peixian CHEN, Nevin Lianwen ZHANG, Kin Man POON, Zhourong CHEN

Research output: Chapter in Book/Report/Conference proceedingChapters

Abstract

Hierarchical latent tree analysis (HLTA) is recently proposed as a new method for topic detection. It differs fundamentally from the LDA-based methods in terms of topic definition, topic-document relationship, and learning method. It has been shown to discover significantly more coherent topics and better topic hierarchies. However, HLTA relies on the Expectation-Maximization (EM) algorithm for parameter estimation and hence is not efficient enough to deal with large datasets. In this paper, we propose a method to drastically speed up HLTA using a technique inspired by the advances in the method of moments. Empirical experiments show that our method greatly improves the efficiency of HLTA. It is as efficient as the state-of-the-art LDA-based method for hierarchical topic detection and finds substantially better topics and topic hierarchies. Copyright © 2016, Association for the Advancement of Artificial Intelligence (www.aaai.org).
Original languageEnglish
Title of host publicationProceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16)
Place of PublicationCalifornia
PublisherAAAI press
Pages1498-1504
ISBN (Print)9781577357605
Publication statusPublished - 2016

Citation

Chen, P., Zhang, N. L., Poon, L. K. M., & Chen, Z. (2016). Progressive EM for latent tree models and hierarchical topic detection. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (pp. 1498-1504). California: AAAI press.

Fingerprint Dive into the research topics of 'Progressive EM for latent tree models and hierarchical topic detection'. Together they form a unique fingerprint.