COGEN: Abductive Commonsense Language Generation

Rohola Zandie, Diwanshu Shekhar, Mohammad Mahoor

Abstract
Reasoning is one of the most important elements in achieving Artificial General Intelligence (AGI), specifically when it comes to Abductive and counterfactual reasoning. In order to introduce these capabilities of reasoning in Natural Language Processing (NLP) models, there have been recent advances towards training NLP models to better perform on two main tasks - Abductive Natural Language Inference (alphaNLI) and Abductive Natural Language Generation Task (alphaNLG). This paper proposes CoGen, a model for both alphaNLI and alphaNLG tasks that employ a novel approach of combining the temporal commonsense reasoning for each observation (before and after a real hypothesis) from pre-trained models with contextual filtering for training. Additionally, we use state-of-the-art semantic entailment to filter out the contradictory hypothesis during the inference. Our experimental results show that CoGen outperforms current models and set a new state of the art in regards to alphaNLI and alphaNLG tasks. We make the source code of CoGen model publicly available for reproducibility and to facilitate relevant future research.
Anthology ID:
2023.acl-short.26
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
295–302
Language:
URL:
https://aclanthology.org/2023.acl-short.26
DOI:
10.18653/v1/2023.acl-short.26
Bibkey:
Cite (ACL):
Rohola Zandie, Diwanshu Shekhar, and Mohammad Mahoor. 2023. COGEN: Abductive Commonsense Language Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 295–302, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
COGEN: Abductive Commonsense Language Generation (Zandie et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2023.acl-short.26.pdf
PDF Search