Learning Multilingual Topics from Incomparable Corpus
This addresses a limitation in crosslingual NLP by allowing more flexible data usage, though it is incremental as it builds on existing topic modeling frameworks.
The paper tackled the problem of multilingual topic models requiring parallel or comparable training corpora by developing a model that only needs a dictionary, enabling learning from incomparable corpora.
Multilingual topic models enable crosslingual tasks by extracting consistent topics from multilingual corpora. Most models require parallel or comparable training corpora, which limits their ability to generalize. In this paper, we first demystify the knowledge transfer mechanism behind multilingual topic models by defining an alternative but equivalent formulation. Based on this analysis, we then relax the assumption of training data required by most existing models, creating a model that only requires a dictionary for training. Experiments show that our new method effectively learns coherent multilingual topics from partially and fully incomparable corpora with limited amounts of dictionary resources.