• Corpus ID: 253018990

Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models

@inproceedings{Stacey2022LogicalRW,
  title={Logical Reasoning with Span-Level Predictions for Interpretable and Robust NLI Models},
  author={Joe Stacey and Pasquale Minervini and Haim Dubossarsky and Marek Rei},
  year={2022}
}
Current Natural Language Inference (NLI) models achieve impressive results, sometimes outperforming humans when evaluating on in-distribution test sets. However, as these models are known to learn from annotation artefacts and dataset biases, it is unclear to what extent the models are learning the task of NLI instead of learning from shallow heuristics in their training data. We address this issue by introducing a logical reasoning framework for NLI, creating highly transparent model decisions… 

Figures and Tables from this paper