InfoCTM: A Mutual Information Maximization Perspective of Cross-Lingual Topic Modeling

Cross-lingual topic models have been prevalent for cross-lingual text analysis by revealing aligned latent topics. However, most existing methods suffer from producing repetitive topics that hinder further and performance decline caused low-coverage dictionaries. In this paper, we propose the Topic Modeling with Mutual Information (InfoCTM). Instead of direct alignment in previous work, a mutual information method. This works as regularization to properly align prevent degenerate representations words, which mitigates issue. To address dictionary issue, vocabulary linking method finds more linked words beyond translations given dictionary. Extensive experiments on English, Chinese, Japanese datasets demonstrate our outperforms state-of-the-art baselines, coherent, diverse, well-aligned showing better transferability classification tasks.