Skip to content

Coherence Regularization for Neural Topic Models

Neural topic models aim to predict the words of a document given the document itself. In such models, perplexity is used as a training criterion, whereas the final quality measure is topic coherence. In this work, we introduce a coherence regularization loss that penalizes incoherent topics during the training of the model. We analyze our approach using coherence and an additional metric – exclusivity, responsible for the uniqueness of the terms in topics. We argue that this combination of metrics is an adequate indicator of the model quality. Our results indicate the effectiveness of our loss and the potential to be used in the future neural topic models.

The paper will be published at the 16th International Symposium on Neural Networks taking place in Moscow. In the meantime, do not hesitate to contact our R&D department at research@euranova.eu to discuss how you can leverage neural topic models in your projects.

Katsiaryna Krasnashchok, Aymen Cherif, Coherence Regularization for Neural Topic Models. in 16th International Symposium on Neural Networks 2019 (ISNN 2019)

Click here to access the paper.

Releated Posts

Internships 2025

You are looking for an internship in an intellectually-stimulating company? are fond of feedback and continuous personal development? want to participate in the development of solutions to address tomorrow’s challenges?
Read More

Insights from IAPP AI Governance Global 2024

In early June, Euranova's CTO Sabri Skhiri, attended the IAPP AI Governance Global 2024 conference in Brussels. In this article, Sabri will delve into some of the keynotes, panels and
Read More