 On the Challenges of Evaluating Compositional Explanations in Multi-Hop
Inference: Relevance, Completeness, and Expert RatingsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Hybrid Autoregressive Inference for Scalable Multi-hop Explanation
RegenerationAAAI Conference on Artificial Intelligence (AAAI), 2021 |
 Do Natural Language Explanations Represent Valid Logical Arguments?
Verifying Entailment in Explainable NLI Gold StandardsInternational Conference on Computational Semantics (IWCS), 2021 |
 Flexible Generation of Natural Language DeductionsConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
