# Context Reinforced Neural Topic Modeling over Short Texts

arXiv: https://arxiv.org/abs/2008.04545 · HTML: https://mlsanity.com/paper/2008.04545/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2020.

## Built on by (most cited first, 10 of 10)

- [Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence](https://mlsanity.com/paper/2107.02173/) (2021)
- [Topic Modelling Meets Deep Neural Networks: A Survey](https://mlsanity.com/paper/2103.00498/) (2021)
- [Are Neural Topic Models Broken?](https://mlsanity.com/paper/2210.16162/) (2022)
- [ANTM: An Aligned Neural Topic Model for Exploring Evolving Topics](https://mlsanity.com/paper/2302.01501/) (2023)
- [Enhancing Short-Text Topic Modeling with LLM-Driven Context Expansion and Prefix-Tuned VAEs](https://mlsanity.com/paper/2410.03071/) (2024)
- [Text characterization based on recurrence networks](https://mlsanity.com/paper/2201.06665/) (2022)
- [Survey of Generative Methods for Social Media Analysis](https://mlsanity.com/paper/2112.07041/) (2021)
- [A Rare Topic Discovery Model for Short Texts Based on Co-occurrence word Network](https://mlsanity.com/paper/2207.00432/) (2022)
- [Let the Pretrained Language Models "Imagine" for Short Texts Topic Modeling](https://mlsanity.com/paper/2310.15420/) (2023)
- [Topic model based on co-occurrence word networks for unbalanced short text datasets](https://mlsanity.com/paper/2311.02566/) (2023)

## Abstract (arXiv)

As one of the prevalent topic mining tools, neural topic modeling has attracted a lot of interests for the advantages of high efficiency in training and strong generalisation abilities. However, due to the lack of context in each short text, the existing neural topic models may suffer from feature sparsity on such documents. To alleviate this issue, we propose a Context Reinforced Neural Topic Model (CRNTM), whose characteristics can be summarized as follows. Firstly, by assuming that each short text covers only a few salient topics, CRNTM infers the topic for each word in a narrow range. Secondly, our model exploits pre-trained word embeddings by treating topics as multivariate Gaussian distributions or Gaussian mixture distributions in the embedding space. Extensive experiments on two benchmark datasets validate the effectiveness of the proposed model on both topic discovery and text classification.