Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained Models
This addresses how multilingual models generalize across languages, which is incremental but provides insights for NLP researchers.
The study investigated whether multilingual pre-trained models encode morphosyntactic information in the same neurons across languages, finding significant cross-lingual overlap that varies by category, language proximity, and data size.
The success of multilingual pre-trained models is underpinned by their ability to learn representations shared by multiple languages even in absence of any explicit supervision. However, it remains unclear how these models learn to generalise across languages. In this work, we conjecture that multilingual pre-trained models can derive language-universal abstractions about grammar. In particular, we investigate whether morphosyntactic information is encoded in the same subset of neurons in different languages. We conduct the first large-scale empirical study over 43 languages and 14 morphosyntactic categories with a state-of-the-art neuron-level probe. Our findings show that the cross-lingual overlap between neurons is significant, but its extent may vary across categories and depends on language proximity and pre-training data size.