A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation

Li Yuan, Yi Cai, Haopeng Ren, Jiexin Wang

Abstract
Generating coherent and credible explanations remains a significant challenge in the field of AI. In recent years, researchers have delved into the utilization of entailment trees to depict explanations, which exhibit a reasoning process of how a hypothesis is deduced from the supporting facts. However, existing models often overlook the importance of generating intermediate conclusions with logical consistency from the given facts, leading to inaccurate conclusions and undermining the overall credibility of entailment trees. To address this limitation, we propose the logical pattern memory pre-trained model (LMPM). LMPM incorporates an external memory structure to learn and store the latent representations of logical patterns, which aids in generating logically consistent conclusions. Furthermore, to mitigate the influence of logically irrelevant domain knowledge in the Wikipedia-based data, we introduce an entity abstraction approach to construct the dataset for pre-training LMPM. The experimental results highlight the effectiveness of our approach in improving the quality of entailment tree generation. By leveraging logical entailment patterns, our model produces more coherent and reasonable conclusions that closely align with the underlying premises.
Anthology ID:
2024.lrec-main.68
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
759–772
Language:
URL:
https://aclanthology.org/2024.lrec-main.68
DOI:
Bibkey:
Cite (ACL):
Li Yuan, Yi Cai, Haopeng Ren, and Jiexin Wang. 2024. A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 759–772, Torino, Italia. ELRA and ICCL.
Cite (Informal):
A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation (Yuan et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.lrec-main.68.pdf
PDF Search