Neural Topic Model via Optimal Transport

TL;DR

This paper introduces a neural topic model based on optimal transport that improves topic coherence, diversity, and document representation, especially for short texts, by directly minimizing OT distance between document and word distributions.

Contribution

It proposes a novel neural topic model leveraging optimal transport theory, avoiding reparameterization, and enhancing performance on short and long documents.

Findings

Outperforms state-of-the-art NTMs in coherence and diversity

Achieves better document representations for short texts

Efficient training with differentiable loss

Abstract

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.