Improving Contextualized Topic Models with Negative Sampling
This is an incremental improvement for researchers and practitioners in natural language processing working with topic modeling.
The paper tackles the problem of improving topic quality in contextualized topic models by introducing a negative sampling mechanism with triplet loss, resulting in increased topic coherence and high diversity across benchmark datasets.
Topic modeling has emerged as a dominant method for exploring large document collections. Recent approaches to topic modeling use large contextualized language models and variational autoencoders. In this paper, we propose a negative sampling mechanism for a contextualized topic model to improve the quality of the generated topics. In particular, during model training, we perturb the generated document-topic vector and use a triplet loss to encourage the document reconstructed from the correct document-topic vector to be similar to the input document and dissimilar to the document reconstructed from the perturbed vector. Experiments for different topic counts on three publicly available benchmark datasets show that in most cases, our approach leads to an increase in topic coherence over that of the baselines. Our model also achieves very high topic diversity.