Retrieval Augmentation for Commonsense Reasoning: A Unified Approach

Wenhao Yu, Chenguang Zhu, Zhihan Zhang, Shuohang Wang, Zhuosheng Zhang, Yuwei Fang, Meng Jiang


Abstract
A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled. However, applying such methods to commonsense reasoning tasks faces two unique challenges, i.e., the lack of a general large-scale corpus for retrieval and a corresponding effective commonsense retriever. In this paper, we systematically investigate how to leverage commonsense knowledge retrieval to improve commonsense reasoning tasks. We proposed a unified framework of retrieval-augmented commonsense reasoning (called RACo), including a newly constructed commonsense corpus with over 20 million documents and novel strategies for training a commonsense retriever. We conducted experiments on four different commonsense reasoning tasks. Extensive evaluation results showed that our proposed RACo can significantly outperform other knowledge-enhanced method counterparts, achieving new SoTA performance on the CommonGen and CREAK leaderboards.
Anthology ID:
2022.emnlp-main.294
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4364–4377
Language:
URL:
https://aclanthology.org/2022.emnlp-main.294
DOI:
Bibkey:
Cite (ACL):
Wenhao Yu, Chenguang Zhu, Zhihan Zhang, Shuohang Wang, Zhuosheng Zhang, Yuwei Fang, and Meng Jiang. 2022. Retrieval Augmentation for Commonsense Reasoning: A Unified Approach. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4364–4377, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Retrieval Augmentation for Commonsense Reasoning: A Unified Approach (Yu et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.emnlp-main.294.pdf