NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation

Peter West, Ronan Bras, Taylor Sorensen, Bill Lin, Liwei Jiang, Ximing Lu, Khyathi Chandu, Jack Hessel, Ashutosh Baheti, Chandra Bhagavatula, Yejin Choi


Abstract
We present NovaCOMET, an open commonsense knowledge model, that combines the best aspects of knowledge and general task models. Compared to previous knowledge models, NovaCOMET allows open-format relations enabling direct application to reasoning tasks; compared to general task models like Flan-T5, it explicitly centers knowledge, enabling superior performance for commonsense reasoning. NovaCOMET leverages the knowledge of opaque proprietary models to create an open knowledge pipeline. First, knowledge is symbolically distilled into NovATOMIC, a publicly-releaseddiscrete knowledge graph which can be audited, critiqued, and filtered. Next, we train NovaCOMET on NovATOMIC by fine-tuning an open-source pretrained model. NovaCOMET uses an open-format training objective, replacing the fixed relation sets of past knowledge models, enabling arbitrary structures within the data to serve as inputs or outputs. The resulting generation model, optionally augmented with human annotation, matches or exceeds comparable open task models like Flan-T5 on a range of commonsense generation tasks. NovaCOMET serves as a counterexample to the contemporary focus on instruction tuning only, demonstrating a distinct advantage to explicitly modeling commonsense knowledge as well.
Anthology ID:
2023.findings-emnlp.80
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1127–1149
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.80
DOI:
10.18653/v1/2023.findings-emnlp.80
Bibkey:
Cite (ACL):
Peter West, Ronan Bras, Taylor Sorensen, Bill Lin, Liwei Jiang, Ximing Lu, Khyathi Chandu, Jack Hessel, Ashutosh Baheti, Chandra Bhagavatula, and Yejin Choi. 2023. NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 1127–1149, Singapore. Association for Computational Linguistics.
Cite (Informal):
NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation (West et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-emnlp.80.pdf