Neural Topic Model via Optimal Transport
This addresses a key bottleneck in text analysis for researchers and practitioners, offering improved topic modeling performance, though it is incremental as it builds on existing NTM approaches.
The authors tackled the problem of existing Neural Topic Models (NTMs) struggling to balance good document representation with coherent/diverse topics, especially on short documents, by proposing a new model using optimal transport theory. The result is a framework that significantly outperforms state-of-the-art NTMs in discovering more coherent and diverse topics and deriving better document representations for both regular and short texts.
Recently, Neural Topic Models (NTMs) inspired by variational autoencoders have obtained increasingly research interest due to their promising results on text analysis. However, it is usually hard for existing NTMs to achieve good document representation and coherent/diverse topics at the same time. Moreover, they often degrade their performance severely on short documents. The requirement of reparameterisation could also comprise their training quality and model flexibility. To address these shortcomings, we present a new neural topic model via the theory of optimal transport (OT). Specifically, we propose to learn the topic distribution of a document by directly minimising its OT distance to the document's word distributions. Importantly, the cost matrix of the OT distance models the weights between topics and words, which is constructed by the distances between topics and words in an embedding space. Our proposed model can be trained efficiently with a differentiable loss. Extensive experiments show that our framework significantly outperforms the state-of-the-art NTMs on discovering more coherent and diverse topics and deriving better document representations for both regular and short texts.