Estimating the Causal Effects of Natural Logic Features in Neural NLI Models
This work addresses interpretability and evaluation issues for researchers in natural language processing, though it is incremental as it adapts existing causal analysis methods to a specific NLI task.
The authors tackled the challenge of evaluating causal effects of semantic features on neural NLI models by focusing on structured reasoning patterns, such as context interventions and word-pair relations, to quantify systematic reasoning failures and model robustness.
Rigorous evaluation of the causal effects of semantic features on language model predictions can be hard to achieve for natural language reasoning problems. However, this is such a desirable form of analysis from both an interpretability and model evaluation perspective, that it is valuable to zone in on specific patterns of reasoning with enough structure and regularity to be able to identify and quantify systematic reasoning failures in widely-used models. In this vein, we pick a portion of the NLI task for which an explicit causal diagram can be systematically constructed: in particular, the case where across two sentences (the premise and hypothesis), two related words/terms occur in a shared context. In this work, we apply causal effect estimation strategies to measure the effect of context interventions (whose effect on the entailment label is mediated by the semantic monotonicity characteristic) and interventions on the inserted word-pair (whose effect on the entailment label is mediated by the relation between these words.). Following related work on causal analysis of NLP models in different settings, we adapt the methodology for the NLI task to construct comparative model profiles in terms of robustness to irrelevant changes and sensitivity to impactful changes.