LogiTorch: A PyTorch-based library for logical reasoning on natural language

Chadi Helwe, Chloé Clavel, Fabian Suchanek


Abstract
Logical reasoning on natural language is one of the most challenging tasks for deep learning models. There has been an increasing interest in developing new benchmarks to evaluate the reasoning capabilities of language models such as BERT. In parallel, new models based on transformers have emerged to achieve ever better performance on these datasets. However, there is currently no library for logical reasoning that includes such benchmarks and models. This paper introduces LogiTorch, a PyTorch-based library that includes different logical reasoning benchmarks, different models, as well as utility functions such as co-reference resolution. This makes it easy to directly use the preprocessed datasets, to run the models, or to finetune them with different hyperparameters. LogiTorch is open source and can be found on GitHub.
Anthology ID:
2022.emnlp-demos.25
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
Month:
December
Year:
2022
Address:
Abu Dhabi, UAE
Editors:
Wanxiang Che, Ekaterina Shutova
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
250–257
Language:
URL:
https://aclanthology.org/2022.emnlp-demos.25
DOI:
10.18653/v1/2022.emnlp-demos.25
Bibkey:
Cite (ACL):
Chadi Helwe, Chloé Clavel, and Fabian Suchanek. 2022. LogiTorch: A PyTorch-based library for logical reasoning on natural language. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 250–257, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
LogiTorch: A PyTorch-based library for logical reasoning on natural language (Helwe et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2022.emnlp-demos.25.pdf