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

arXiv:2304.03544v2 Announce Type: replace
Abstract: 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 analysis and performance decline caused by low-coverage dictionaries. In this paper, we propose the Cross-lingual Topic Modeling with Mutual Information (InfoCTM). Instead of the direct alignment in previous work, we propose a topic alignment with mutual information method. This works as a regularization to properly align topics and …

abstract analysis arxiv coverage cross-lingual cs.cl hinder however information low modeling paper performance perspective text topic modeling topics type