Naturalistic Causal Probing for Morpho-Syntax
This work addresses the need for more reliable probing techniques in NLP to better interpret pre-trained models, though it is incremental as it builds on existing probing methodologies.
The authors tackled the problem of understanding limitations in probing methods for deep neural models by introducing a naturalistic causal probing framework that intervenes on morpho-syntactic features in sentences. They applied this to analyze grammatical gender and number effects in Spanish pre-trained models, finding that naturalistic interventions lead to stable causal effect estimates.
Probing has become a go-to methodology for interpreting and analyzing deep neural models in natural language processing. However, there is still a lack of understanding of the limitations and weaknesses of various types of probes. In this work, we suggest a strategy for input-level intervention on naturalistic sentences. Using our approach, we intervene on the morpho-syntactic features of a sentence, while keeping the rest of the sentence unchanged. Such an intervention allows us to causally probe pre-trained models. We apply our naturalistic causal probing framework to analyze the effects of grammatical gender and number on contextualized representations extracted from three pre-trained models in Spanish: the multilingual versions of BERT, RoBERTa, and GPT-2. Our experiments suggest that naturalistic interventions lead to stable estimates of the causal effects of various linguistic properties. Moreover, our experiments demonstrate the importance of naturalistic causal probing when analyzing pre-trained models.