Shaheen Syed published a paper at the IEEE International Conference on Semantic Computing (ICSC 2018)

Our early stage researcher Shaheen Syed published and presented his latest paper entitled “Selecting Priors for Latent Dirichlet Allocation” at the IEEE International Conference on Semantic Computing (ICSC 2018) held in Laguna Hills, California, USA (Jan 31 – Feb 2, 2018).

His work explores symmetrical and asymmetrical Dirichlet priors when utilizing the topic model latent Dirichlet allocation (LDA). Since LDA is a Bayesian topic model, prior knowledge for words in topics, and topics in documents can be incorporated and his paper shows what the practical implications on the quality of topics can be when choosing one prior over the other.

The paper can be downloaded from here:
Selecting Priors for Latent Dirichlet Allocation

Paper abstract:

Latent Dirichlet Allocation (LDA) has gained much attention from researchers and is increasingly being applied to uncover underlying semantic structures from a variety of corpora. However, nearly all researchers use symmetrical Dirichlet priors, often unaware of the underlying practical implications that they bear. This research is the first to explore symmetrical and asymmetrical Dirichlet priors on topic coherence and human topic ranking when uncovering latent semantic structures from scientific research articles. More specifically, we examine the practical effects of several classes of Dirichlet priors on 2000 LDA models created from abstract and full-text research articles. Our results show that symmetrical or asymmetrical priors on the document–topic distribution or the topic–word distribution for full-text data have little effect on topic coherence scores and human topic ranking. In contrast, asymmetrical priors on the document–topic distribution for abstract data show a significant increase in topic coherence scores and improved human topic ranking compared to a symmetrical prior. Symmetrical or asymmetrical priors on the topic–word distribution show no real benefits for both abstract and full-text data.

Syed, S., & Spruit, M. (2018). Selecting Priors for Latent Dirichlet Allocation. In The 12th IEEE International Conference on Semantic Computing (pp. 194–202). Laguna Hills, CA, USA: IEEE. http://doi.org/10.1109/ICSC.2018.00035

2018-05-22T12:24:06+00:00 February 3rd, 2018|

About the Author: