Research Vision

Knowledge graphs provide a semi-structured way for representing commonsense concepts. This structure gives a different viewpoint than other knowledge sources such as large textual corpora; however, what kinds of knowledge to represent and how best to incorporate them into modern neural methods remains an important question for research. To tackle it, we're currently building and releasing resources that explore different aspects of commonsense, such as information about social situations, mental states, and causal relationships.

Papers

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

Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, and 3 more... AAAI  2019

COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs

Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and 1 more... AAAI  2021

Symbolic Knowledge Distillation: from General Language Models to Commonsense Models

Peter West, Chandrasekhar Bhagavatula, Jack Hessel, Jena D. Hwang, Liwei Jiang, Ronan Le Bras, and 3 more... NAACL  2021

Knowledge Graphs and Resources