Knowledge-driven Natural Language Understanding of English Text and its Applications

Authors

  • Kinjal Basu University of Texas at Dallas
  • Sarat Chandra Varanasi University of Texas at Dallas
  • Farhad Shakerin University of Texas at Dallas
  • Joaquín Arias Universidad Rey Juan Carlos
  • Gopal Gupta University of Texas at Dallas

Keywords:

Question Answering, Common-Sense Reasoning

Abstract

Understanding the meaning of a text is a fundamental challenge of natural language understanding (NLU) research. An ideal NLU system should process a language in a way that is not exclusive to a single task or a dataset. Keeping this in mind, we have introduced a novel knowledge driven semantic representation approach for English text. By leveraging the VerbNet lexicon, we are able to map syntax tree of the text to its commonsense meaning represented using basic knowledge primitives. The general purpose knowledge represented from our approach can be used to build any reasoning based NLU system that can also provide justification. We applied this approach to construct two NLU applications that we present here: SQuARE (Semantic-based Question Answering and Reasoning Engine) and StaCACK (Stateful Conversational Agent using Commonsense Knowledge). Both these systems work by ``truly understanding'' the natural language text they process and both provide natural language explanations for their responses while maintaining high accuracy.

Downloads

Published

2021-05-18

How to Cite

Basu, K., Varanasi, S. C., Shakerin, F., Arias, J., & Gupta, G. (2021). Knowledge-driven Natural Language Understanding of English Text and its Applications. Proceedings of the AAAI Conference on Artificial Intelligence, 35(14), 12554-12563. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17488

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing I