ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning

  • Maarten Sap University of Washington
  • Ronan Le Bras Allen Institute for AI
  • Emily Allaway University of Washington
  • Chandra Bhagavatula Allen Institute for AI
  • Nicholas Lourie Allen Institute for AI
  • Hannah Rashkin University of Washington
  • Brendan Roof Allen Institute for AI
  • Noah A. Smith University of Washington
  • Yejin Choi University of Washington

Abstract

We present ATOMIC, an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. Compared to existing resources that center around taxonomic knowledge, ATOMIC focuses on inferential knowledge organized as typed if-then relations with variables (e.g., “if X pays Y a compliment, then Y will likely return the compliment”). We propose nine if-then relation types to distinguish causes vs. effects, agents vs. themes, voluntary vs. involuntary events, and actions vs. mental states. By generatively training on the rich inferential knowledge described in ATOMIC, we show that neural models can acquire simple commonsense capabilities and reason about previously unseen events. Experimental results demonstrate that multitask models that incorporate the hierarchical structure of if-then relation types lead to more accurate inference compared to models trained in isolation, as measured by both automatic and human evaluation.

Published
2019-07-17
Section
AAAI Technical Track: Knowledge Representation and Reasoning