Is neural language acquisition similar to natural? A chronological probing study
This work addresses the problem of understanding how neural models learn language for researchers in NLP and linguistics, but it is incremental as it builds on existing probing methodologies.
The study investigated whether transformer language models acquire linguistic knowledge similarly to natural language acquisition by probing MultiBERT and T5 models during training, finding that linguistic information is captured early and across multiple language levels, though with inconsistencies on some tasks.
The probing methodology allows one to obtain a partial representation of linguistic phenomena stored in the inner layers of the neural network, using external classifiers and statistical analysis. Pre-trained transformer-based language models are widely used both for natural language understanding (NLU) and natural language generation (NLG) tasks making them most commonly used for downstream applications. However, little analysis was carried out, whether the models were pre-trained enough or contained knowledge correlated with linguistic theory. We are presenting the chronological probing study of transformer English models such as MultiBERT and T5. We sequentially compare the information about the language learned by the models in the process of training on corpora. The results show that 1) linguistic information is acquired in the early stages of training 2) both language models demonstrate capabilities to capture various features from various levels of language, including morphology, syntax, and even discourse, while they also can inconsistently fail on tasks that are perceived as easy. We also introduce the open-source framework for chronological probing research, compatible with other transformer-based models. https://github.com/EkaterinaVoloshina/chronological_probing