NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning

Zeming Chen, Qiyue Gao, Lawrence S. Moss


Abstract
Deep learning (DL) based language models achieve high performance on various benchmarks for Natural Language Inference (NLI). And at this time, symbolic approaches to NLI are receiving less attention. Both approaches (symbolic and DL) have their advantages and weaknesses. However, currently, no method combines them in a system to solve the task of NLI. To merge symbolic and deep learning methods, we propose an inference framework called NeuralLog, which utilizes both a monotonicity-based logical inference engine and a neural network language model for phrase alignment. Our framework models the NLI task as a classic search problem and uses the beam search algorithm to search for optimal inference paths. Experiments show that our joint logic and neural inference system improves accuracy on the NLI task and can achieve state-of-art accuracy on the SICK and MED datasets.
Anthology ID:
2021.starsem-1.7
Volume:
Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics
Month:
August
Year:
2021
Address:
Online
Venues:
*SEM | ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
78–88
Language:
URL:
https://aclanthology.org/2021.starsem-1.7
DOI:
10.18653/v1/2021.starsem-1.7
Bibkey:
Cite (ACL):
Zeming Chen, Qiyue Gao, and Lawrence S. Moss. 2021. NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 78–88, Online. Association for Computational Linguistics.
Cite (Informal):
NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning (Chen et al., *SEM 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.starsem-1.7.pdf
Code
 eric11eca/NeuralLog
Data
MEDSICK