Application of Neuro-Symbolic Reasoning in Natural Language Processing

Shivani G. Aithal, Abishek B. Rao, C. B. Chandrakala, Sanjay Singh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Commonsense reasoning is a crucial part of human intelligence. It has been a goal in the study of artificial intelligence to develop machines mimicking commonsense reasoning at par with humans. The deep learning models have advanced in many natural language processing tasks. However, they lack logical reasoning ability. Symbolic artificial intelligence has the potential reasoning ability wherein logic is used to reason efficiently. This led to the rise of neuro-symbolic reasoning, which is an integration of symbolic logic with deep learning. In this paper, we have experimented with the BERT, RoBERTa and GPT-J language models for question answering task to check their reasoning ability and found that they lack the reasoning ability. This paper compares the performance of the BERT, RoBERTa and GPT-J question-answering models with the neuro-symbolic reasoning model using logical neural networks. It is found that the neuro-symbolic reasoning model has the reasoning ability like humans, which infers that the neuro-symbolic reasoning model can effectively handle logical reasoning and is a key to the future of artificial intelligence.

Original languageEnglish
Title of host publication2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665473125
DOIs
Publication statusPublished - 2022
Event6th IEEE Conference on Information and Communication Technology, CICT 2022 - Gwalior, India
Duration: 18-11-202220-11-2022

Publication series

Name2022 IEEE 6th Conference on Information and Communication Technology, CICT 2022

Conference

Conference6th IEEE Conference on Information and Communication Technology, CICT 2022
Country/TerritoryIndia
CityGwalior
Period18-11-2220-11-22

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems
  • Modelling and Simulation
  • Instrumentation

Fingerprint

Dive into the research topics of 'Application of Neuro-Symbolic Reasoning in Natural Language Processing'. Together they form a unique fingerprint.

Cite this