Conversational AI : Open Domain Question Answering and Commonsense Reasoning

TL;DR

This paper discusses developing a human-like open domain question answering system that employs automated commonsense reasoning to understand dialogues and infer unstated facts, aiming for more natural and robust interactions.

Contribution

It introduces a novel approach integrating automated commonsense reasoning into conversational AI for improved understanding and response generation.

Findings

Enhanced understanding of dialogues through commonsense inference

Improved robustness in question answering systems

Potential for more human-like conversational interactions

Abstract

Our research is focused on making a human-like question answering system which can answer rationally. The distinguishing characteristic of our approach is that it will use automated common sense reasoning to truly "understand" dialogues, allowing it to converse like a human. Humans often make many assumptions during conversations. We infer facts not told explicitly by using our common sense. Incorporating commonsense knowledge in a question answering system will simply make it more robust.