MorphNLI: A Stepwise Approach to Natural Language Inference Using Text Morphing
It addresses NLI classification, particularly for cross-domain robustness, with incremental improvements.
The paper tackles natural language inference by introducing MorphNLI, a stepwise method that morphs premises into hypotheses to classify entailment, achieving up to 12.6% relative improvement in cross-domain settings.
We introduce MorphNLI, a modular step-by-step approach to natural language inference (NLI). When classifying the premise-hypothesis pairs into {entailment, contradiction, neutral}, we use a language model to generate the necessary edits to incrementally transform (i.e., morph) the premise into the hypothesis. Then, using an off-the-shelf NLI model we track how the entailment progresses with these atomic changes, aggregating these intermediate labels into a final output. We demonstrate the advantages of our proposed method particularly in realistic cross-domain settings, where our method always outperforms strong baselines with improvements up to 12.6% (relative). Further, our proposed approach is explainable as the atomic edits can be used to understand the overall NLI label.