Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot

TL;DR

This paper introduces a novel ontology-free dialogue state tracking method for goal-oriented chatbots, leveraging instruction tuning, prompt strategies, and a VGAE to improve adaptability and accuracy in open-domain conversations.

Contribution

It presents a new approach combining instruction tuning, prompt engineering, and graph auto-encoders to enhance dialogue state tracking without relying on predefined ontologies.

Findings

Achieved a state-of-the-art JGA of 42.57% in ontology-less DST.

Demonstrated strong performance in open-domain real-world conversations.

Outperformed existing models relying on fixed ontologies.

Abstract

Goal-oriented chatbots are essential for automating user tasks, such as booking flights or making restaurant reservations. A key component of these systems is Dialogue State Tracking (DST), which interprets user intent and maintains the dialogue state. However, existing DST methods often rely on fixed ontologies and manually compiled slot values, limiting their adaptability to open-domain dialogues. We propose a novel approach that leverages instruction tuning and advanced prompt strategies to enhance DST performance, without relying on any predefined ontologies. Our method enables Large Language Model (LLM) to infer dialogue states through carefully designed prompts and includes an anti-hallucination mechanism to ensure accurate tracking in diverse conversation contexts. Additionally, we employ a Variational Graph Auto-Encoder (VGAE) to model and predict subsequent user intent. Our approach achieved state-of-the-art with a JGA of 42.57% outperforming existing ontology-less DST models, and performed well in open-domain real-world conversations. This work presents a significant advancement in creating more adaptive and accurate goal-oriented chatbots.