Thinking Like a Skeptic : Defeasible Inference in Natural Language

Rachel Rudinger, Vered Shwartz, Jena D. Hwang, Chandra Bhagavatula, Maxwell Forbes, Ronan Le Bras, Noah A. Smith, Yejin Choi


Abstract
Defeasible inference is a mode of reasoning in which an inference (X is a bird, therefore X flies) may be weakened or overturned in light of new evidence (X is a penguin). Though long recognized in classical AI and philosophy, defeasible inference has not been extensively studied in the context of contemporary data-driven research on natural language inference and commonsense reasoning. We introduce Defeasible NLI (abbreviated -NLI), a dataset for defeasible inference in natural language. Defeasible NLI contains extensions to three existing inference datasets covering diverse modes of reasoning : common sense, natural language inference, and social norms. From Defeasible NLI, we develop both a classification and generation task for defeasible inference, and demonstrate that the generation task is much more challenging. Despite lagging human performance, however, generative models trained on this data are capable of writing sentences that weaken or strengthen a specified inference up to 68 % of the time.\\delta-NLI), a dataset for defeasible inference in natural language. Defeasible NLI contains extensions to three existing inference datasets covering diverse modes of reasoning: common sense, natural language inference, and social norms. From Defeasible NLI, we develop both a classification and generation task for defeasible inference, and demonstrate that the generation task is much more challenging. Despite lagging human performance, however, generative models trained on this data are capable of writing sentences that weaken or strengthen a specified inference up to 68% of the time.
Anthology ID:
2020.findings-emnlp.418
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Venues:
EMNLP | Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4661–4675
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.418
DOI:
10.18653/v1/2020.findings-emnlp.418
Bibkey:
Cite (ACL):
Rachel Rudinger, Vered Shwartz, Jena D. Hwang, Chandra Bhagavatula, Maxwell Forbes, Ronan Le Bras, Noah A. Smith, and Yejin Choi. 2020. Thinking Like a Skeptic : Defeasible Inference in Natural Language. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4661–4675, Online. Association for Computational Linguistics.
Cite (Informal):
Thinking Like a Skeptic : Defeasible Inference in Natural Language (Rudinger et al., Findings 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.findings-emnlp.418.pdf
Video:
 https://slideslive.com/38940700
Code
 rudinger/defeasible-nli
Data
SNLI
Terminologies: