An Empirical Study on Crosslingual Transfer in Probabilistic Topic Models
This work addresses the problem of unclear model applicability under varied training conditions for researchers and practitioners in crosslingual NLP, but it is incremental as it focuses on empirical evaluation rather than introducing new methods.
The paper systematically studied knowledge transfer mechanisms in multilingual probabilistic topic models, conducting experiments with four models across ten languages to provide empirical insights for model selection and development.
Probabilistic topic modeling is a popular choice as the first step of crosslingual tasks to enable knowledge transfer and extract multilingual features. While many multilingual topic models have been developed, their assumptions on the training corpus are quite varied, and it is not clear how well the models can be applied under various training conditions. In this paper, we systematically study the knowledge transfer mechanisms behind different multilingual topic models, and through a broad set of experiments with four models on ten languages, we provide empirical insights that can inform the selection and future development of multilingual topic models.