From Knowledge Augmentation to Multi-tasking: Towards Human-like Dialogue Systems

TL;DR

This paper reviews progress in developing human-like dialogue systems, emphasizing knowledge augmentation and multi-tasking approaches inspired by AI methodologies to bridge the gap to human-level conversation.

Contribution

It introduces a comprehensive perspective on advancing dialogue systems through knowledge augmentation and multi-tasking, highlighting novel integrations inspired by AI techniques.

Findings

Deep learning significantly improved dialogue capabilities.

Knowledge augmentation enhances contextual understanding.

Multi-tasking enables more versatile dialogue interactions.

Abstract

The goal of building dialogue agents that can converse with humans naturally has been a long-standing dream of researchers since the early days of artificial intelligence. The well-known Turing Test proposed to judge the ultimate validity of an artificial intelligence agent on the indistinguishability of its dialogues from humans'. It should come as no surprise that human-level dialogue systems are very challenging to build. But, while early effort on rule-based systems found limited success, the emergence of deep learning enabled great advance on this topic. In this thesis, we focus on methods that address the numerous issues that have been imposing the gap between artificial conversational agents and human-level interlocutors. These methods were proposed and experimented with in ways that were inspired by general state-of-the-art AI methodologies. But they also targeted the characteristics that dialogue systems possess.