S2vNTM: Semi-supervised vMF Neural Topic Modeling

TL;DR

S2vNTM introduces a semi-supervised neural topic model that uses seed keywords to improve topic quality and classification accuracy while reducing training resources and time.

Contribution

It proposes a novel semi-supervised vMF neural topic model that effectively incorporates human knowledge and enhances efficiency compared to existing methods.

Findings

Outperforms existing semi-supervised topic models in accuracy.

At least twice as fast as baseline methods.

Effective with limited seed keywords.

Abstract

Language model based methods are powerful techniques for text classification. However, the models have several shortcomings. (1) It is difficult to integrate human knowledge such as keywords. (2) It needs a lot of resources to train the models. (3) It relied on large text data to pretrain. In this paper, we propose Semi-Supervised vMF Neural Topic Modeling (S2vNTM) to overcome these difficulties. S2vNTM takes a few seed keywords as input for topics. S2vNTM leverages the pattern of keywords to identify potential topics, as well as optimize the quality of topics' keywords sets. Across a variety of datasets, S2vNTM outperforms existing semi-supervised topic modeling methods in classification accuracy with limited keywords provided. S2vNTM is at least twice as fast as baselines.