Knowledge-driven Natural Language Understanding of English Text and its Applications
This work addresses the problem of building versatile and interpretable NLU systems for applications like question answering and conversational agents, though it appears incremental as it builds on existing lexicons and semantic representations.
The paper tackles the challenge of creating a general-purpose natural language understanding system by introducing a knowledge-driven semantic representation approach using VerbNet and basic knowledge primitives. It results in two applications, SQuARE and StaCACK, that achieve high accuracy and provide natural language explanations for their responses.
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.