Supporting Context Monotonicity Abstractions in Neural NLI Models
This work addresses a specific bottleneck in NLI for linguists and AI researchers, offering an incremental improvement in handling logical regularities.
The paper tackled the problem of improving neural NLI models' performance on examples requiring monotonicity reasoning, by reframing context monotonicity classification for compatibility with transformers and adding it to training, resulting in enhanced performance on targeted challenge sets.
Natural language contexts display logical regularities with respect to substitutions of related concepts: these are captured in a functional order-theoretic property called monotonicity. For a certain class of NLI problems where the resulting entailment label depends only on the context monotonicity and the relation between the substituted concepts, we build on previous techniques that aim to improve the performance of NLI models for these problems, as consistent performance across both upward and downward monotone contexts still seems difficult to attain even for state-of-the-art models. To this end, we reframe the problem of context monotonicity classification to make it compatible with transformer-based pre-trained NLI models and add this task to the training pipeline. Furthermore, we introduce a sound and complete simplified monotonicity logic formalism which describes our treatment of contexts as abstract units. Using the notions in our formalism, we adapt targeted challenge sets to investigate whether an intermediate context monotonicity classification task can aid NLI models' performance on examples exhibiting monotonicity reasoning.