Linguistic Profiling of a Neural Language Model
This work provides insights into model interpretability for NLP researchers, but it is incremental as it builds on existing probing methods.
The paper investigates how a neural language model (BERT) encodes linguistic knowledge before and after fine-tuning, showing it loses some information during task-specific training, and finds that higher linguistic encoding correlates with better prediction accuracy in classification tasks.
In this paper we investigate the linguistic knowledge learned by a Neural Language Model (NLM) before and after a fine-tuning process and how this knowledge affects its predictions during several classification problems. We use a wide set of probing tasks, each of which corresponds to a distinct sentence-level feature extracted from different levels of linguistic annotation. We show that BERT is able to encode a wide range of linguistic characteristics, but it tends to lose this information when trained on specific downstream tasks. We also find that BERT's capacity to encode different kind of linguistic properties has a positive influence on its predictions: the more it stores readable linguistic information of a sentence, the higher will be its capacity of predicting the expected label assigned to that sentence.