Multilingual and Multimodal Topic Modelling with Pretrained Embeddings
This work addresses the challenge of analyzing comparable multilingual and multimodal data for researchers in NLP and computer vision, though it is incremental as it builds on existing topic modeling and embedding techniques.
The paper tackles the problem of modeling topics across multiple languages and modalities by introducing M3L-Contrast, a neural topic model that maps texts and images into a shared topic space using pretrained embeddings, resulting in competitive performance with zero-shot models for multilingual data and significantly better performance for multimodal data.
This paper presents M3L-Contrast -- a novel multimodal multilingual (M3L) neural topic model for comparable data that maps texts from multiple languages and images into a shared topic space. Our model is trained jointly on texts and images and takes advantage of pretrained document and image embeddings to abstract the complexities between different languages and modalities. As a multilingual topic model, it produces aligned language-specific topics and as multimodal model, it infers textual representations of semantic concepts in images. We demonstrate that our model is competitive with a zero-shot topic model in predicting topic distributions for comparable multilingual data and significantly outperforms a zero-shot model in predicting topic distributions for comparable texts and images. We also show that our model performs almost as well on unaligned embeddings as it does on aligned embeddings.