Corpus ID: 201058651

Abductive Commonsense Reasoning

@article{Bhagavatula2020AbductiveCR,
  title={Abductive Commonsense Reasoning},
  author={Chandra Bhagavatula and Ronan Le Bras and Chaitanya Malaviya and Keisuke Sakaguchi and Ari Holtzman and Hannah Rashkin and Doug Downey and S. Yih and Yejin Choi},
  journal={ArXiv},
  year={2020},
  volume={abs/1908.05739}
}
  • Chandra Bhagavatula, Ronan Le Bras, +6 authors Yejin Choi
  • Published 2020
  • Computer Science
  • ArXiv
  • Abductive reasoning is inference to the most plausible explanation. [...] Key Method We conceptualize a new task of Abductive NLI and introduce a challenge dataset, ART, that consists of over 20k commonsense narrative contexts and 200k explanations, formulated as multiple choice questions for easy automatic evaluation. We establish comprehensive baseline performance on this task based on state-of-the-art NLI and language models, which leads to 68.9% accuracy, well below human performance (91.4%). Our analysis…Expand Abstract
    68 Citations
    Thinking Like a Skeptic: Defeasible Inference in Natural Language
    • 3
    • PDF
    Social Commonsense Reasoning with Multi-Head Knowledge Attention
    • 1
    • PDF
    Natural Language Inference in Context - Investigating Contextual Reasoning over Long Texts
    • Highly Influenced
    • PDF
    L2R²: Leveraging Ranking for Abductive Reasoning
    • 1
    • Highly Influenced
    • PDF
    Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision
    • 1
    • PDF
    ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language
    • PDF
    XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning
    • 13
    • PDF

    References

    SHOWING 1-10 OF 52 REFERENCES
    Robust Textual Inference Via Learning and Abductive Reasoning
    • 75
    • PDF
    ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning
    • 180
    • PDF
    One Hundred Challenge Problems for Logical Formalizations of Commonsense Psychology
    • 24
    SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference
    • 274
    • PDF
    e-SNLI: Natural Language Inference with Natural Language Explanations
    • 81
    • PDF
    Annotation Artifacts in Natural Language Inference Data
    • 374
    • Highly Influential
    • PDF
    Natural Logic for Textual Inference
    • 159
    • PDF
    Ordinal Common-sense Inference
    • 68
    • PDF
    A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories
    • 210
    • Highly Influential
    • PDF