English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Embedding-based neural topic models could explicitly represent words andtopics by embedding them to a homogeneous feature space, which shows higherinterpretability. However, there are no explicit constraints for the trainingof embeddings, leading to a larger optimization space. Also, a cleardescription of the changes in embeddings and the impact on model performance isstill lacking. In this paper, we propose an embedding regularized neural topicmodel, which applies the specially designed training constraints on wordembedding and topic embedding to reduce the optimization space of parameters.To reveal the changes and roles of embeddings, we introduce \textbf{uniformity}into the embedding-based neural topic model as the evaluation metric ofembedding space. On this basis, we describe how embeddings tend to changeduring training via the changes in the uniformity of embeddings. Furthermore,we demonstrate the impact of changes in embeddings in embedding-based neuraltopic models through ablation studies. The results of experiments on twomainstream datasets indicate that our model significantly outperforms baselinemodels in terms of the harmony between topic quality and document modeling.This work is the first attempt to exploit uniformity to explore changes inembeddings of embedding-based neural topic models and their impact on modelperformance to the best of our knowledge.

Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models