English

Differentiable Open-Ended Commonsense Reasoning

Computation and Language 2021-06-08 v2 Artificial Intelligence Machine Learning

Abstract

Current commonsense reasoning research focuses on developing models that use commonsense knowledge to answer multiple-choice questions. However, systems designed to answer multiple-choice questions may not be useful in applications that do not provide a small list of candidate answers to choose from. As a step towards making commonsense reasoning research more realistic, we propose to study open-ended commonsense reasoning (OpenCSR) -- the task of answering a commonsense question without any pre-defined choices -- using as a resource only a corpus of commonsense facts written in natural language. OpenCSR is challenging due to a large decision space, and because many questions require implicit multi-hop reasoning. As an approach to OpenCSR, we propose DrFact, an efficient Differentiable model for multi-hop Reasoning over knowledge Facts. To evaluate OpenCSR methods, we adapt several popular commonsense reasoning benchmarks, and collect multiple new answers for each test question via crowd-sourcing. Experiments show that DrFact outperforms strong baseline methods by a large margin.

Keywords

Cite

@article{arxiv.2010.14439,
  title  = {Differentiable Open-Ended Commonsense Reasoning},
  author = {Bill Yuchen Lin and Haitian Sun and Bhuwan Dhingra and Manzil Zaheer and Xiang Ren and William W. Cohen},
  journal= {arXiv preprint arXiv:2010.14439},
  year   = {2021}
}

Comments

Accepted to NAACL 2021. Project website: https://open-csr.github.io

R2 v1 2026-06-23T19:41:34.755Z