SQuARE: Semantics-based Question Answering and Reasoning Engine

09/22/2020
by   Kinjal Basu, et al.
0

Understanding the meaning of a text is a fundamental challenge of natural language understanding (NLU) and from its early days, it has received significant attention through question answering (QA) tasks. We introduce a general semantics-based framework for natural language QA and also describe the SQuARE system, an application of this framework. The framework is based on the denotational semantics approach widely used in programming language research. In our framework, valuation function maps syntax tree of the text to its commonsense meaning represented using basic knowledge primitives (the semantic algebra) coded using answer set programming (ASP). We illustrate an application of this framework by using VerbNet primitives as our semantic algebra and a novel algorithm based on partial tree matching that generates an answer set program that represents the knowledge in the text. A question posed against that text is converted into an ASP query using the same framework and executed using the s(CASP) goal-directed ASP system. Our approach is based purely on (commonsense) reasoning. SQuARE achieves 100 of bAbI QA tasks that we have tested. The significance of our work is that, unlike other machine learning based approaches, ours is based on "understanding" the text and does not require any training. SQuARE can also generate an explanation for an answer while maintaining high accuracy.

READ FULL TEXT
research
01/27/2021

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

Understanding the meaning of a text is a fundamental challenge of natura...
research
12/21/2021

An ASP-based Approach to Answering Natural Language Questions for Texts

An approach based on answer set programming (ASP) is proposed in this pa...
research
05/01/2019

Declarative Question Answering over Knowledge Bases containing Natural Language Text with Answer Set Programming

While in recent years machine learning (ML) based approaches have been t...
research
02/07/2023

Reliable Natural Language Understanding with Large Language Models and Answer Set Programming

Humans understand language by extracting information (meaning) from sent...
research
03/15/2023

Automated Interactive Domain-Specific Conversational Agents that Understand Human Dialogs

Achieving human-like communication with machines remains a classic, chal...
research
10/21/2022

WikiWhy: Answering and Explaining Cause-and-Effect Questions

As large language models (LLMs) grow larger and more sophisticated, asse...
research
08/25/2022

Automating UAV Flight Readiness Approval using Goal-Directed Answer Set Programming

We present a novel application of Goal-Directed Answer Set Programming t...

Please sign up or login with your details

Forgot password? Click here to reset