A Joint Learning Approach for Semi-supervised Neural Topic Modeling
Jeffrey Chiu, Rajat Mittal, Neehal Tumma, Abhishek Sharma, Finale Doshi-Velez
Abstract
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.- Anthology ID:
- 2022.spnlp-1.5
- Volume:
- Proceedings of the Sixth Workshop on Structured Prediction for NLP
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- spnlp
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 40–51
- Language:
- URL:
- https://aclanthology.org/2022.spnlp-1.5
- DOI:
- 10.18653/v1/2022.spnlp-1.5
- Cite (ACL):
- Jeffrey Chiu, Rajat Mittal, Neehal Tumma, Abhishek Sharma, and Finale Doshi-Velez. 2022. A Joint Learning Approach for Semi-supervised Neural Topic Modeling. In Proceedings of the Sixth Workshop on Structured Prediction for NLP, pages 40–51, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- A Joint Learning Approach for Semi-supervised Neural Topic Modeling (Chiu et al., spnlp 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.spnlp-1.5.pdf