With the rapid advancement of technology, there has been a significant increase in the availability of text documents in digital format. Categorizing these documents based on their underlying content is crucial to facilitate easy access for users. However, manual labeling of these documents with their corresponding domain tags can be laborious and time-consuming due to the large volume of the corpus. Topic modeling techniques have emerged as a valuable tool in this context, as they can extract latent topics from a large corpus and label the documents with their dominant topics in an unsupervised manner. While traditional models pose computational challenges, neural topic models offer enhanced flexibility and scalability. Negative sampling-based models emphasize learning the document similarities and distinctions, thereby improving the quality of the learned topics. This article conducts an empirical evaluation of several neural topic models based on negative sampling, implemented withi...

Negative sampling has emerged as an effective technique that enables deep learning models to learn better representations by introducing the paradigm of “learn-to-compare.” The goal of this approach is to add robustness to deep learning models to learn better representation by comparing the positive samples against the negative ones. Despite its numerous demonstrations in various areas of computer vision and natural language processing, a comprehensive study of the effect of negative sampling in an unsupervised domain such as topic modeling has not been well explored. In this article, we present a comprehensive analysis of the impact of different negative sampling strategies on neural topic models. We compare the performance of several popular neural topic models by incorporating a negative sampling technique in the decoder of variational autoencoder-based neural topic models. Experiments on four publicly available datasets demonstrate that integrating negative sampling into topic mode...