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

TL;DR

This paper introduces a knowledge-driven semantic representation method for English text that leverages VerbNet to enable reasoning and explanation in NLU applications, demonstrated through question answering and conversational agents.

Contribution

The paper presents a novel approach that maps syntax trees to commonsense meanings using VerbNet, facilitating reasoning and explanation in NLU systems.

Findings

Achieved high accuracy in question answering and conversational tasks.

Enabled systems to provide natural language explanations.

Demonstrated versatility across multiple NLU applications.

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.