Topic models are some of the most popular ways to represent textual data in an interpret-able manner. Recently, advances in deep generative models, specifically auto-encoding variational Bayes (AEVB), have led to the introduction of unsupervised neural topic models, which leverage deep generative models as opposed to traditional statistics-based topic models. We extend upon these neural topic models by introducing the Label-Indexed Neural Topic Model (LI-NTM), which is, to the extent of our knowledge, the first effective upstream semi-supervised neural topic model. We find that LI-NTM outperforms existing neural topic models in document reconstruction benchmarks, with the most notable results in low labeled data regimes and for data-sets with informative labels; furthermore, our jointly learned classifier outperforms baseline classifiers in ablation studies.
@article{arxiv.2204.03208,
title = {A Joint Learning Approach for Semi-supervised Neural Topic Modeling},
author = {Jeffrey Chiu and Rajat Mittal and Neehal Tumma and Abhishek Sharma and Finale Doshi-Velez},
journal= {arXiv preprint arXiv:2204.03208},
year = {2022}
}
Comments
To appear in the 6th ACL Workshop on Structured Prediction for NLP (SPNLP)