CASPR: A Commonsense Reasoning-based Conversational Socialbot

TL;DR

CASPR is a socialbot that employs automated commonsense reasoning to understand and engage in human-like conversations, aiming to improve conversational quality and learning capabilities.

Contribution

It introduces a novel approach using conversational knowledge templates for commonsense reasoning in socialbots, enhancing understanding and dialogue management.

Findings

CASPR demonstrates improved conversational understanding.

The system effectively learns new knowledge during interactions.

Performance results show competitive engagement levels.

Abstract

We report on the design and development of the CASPR system, a socialbot designed to compete in the Amazon Alexa Socialbot Challenge 4. CASPR's distinguishing characteristic is that it will use automated commonsense reasoning to truly "understand" dialogs, allowing it to converse like a human. Three main requirements of a socialbot are that it should be able to "understand" users' utterances, possess a strategy for holding a conversation, and be able to learn new knowledge. We developed techniques such as conversational knowledge template (CKT) to approximate commonsense reasoning needed to hold a conversation on specific topics. We present the philosophy behind CASPR's design as well as details of its implementation. We also report on CASPR's performance as well as discuss lessons learned.