A Comparative Study on Language Models for Task-Oriented Dialogue Systems

TL;DR

This paper compares recent pretrained language models like BART and T5 for end-to-end task-oriented dialogue systems, demonstrating their superior performance and ability to generate accurate, fluent responses without dialogue state tracking.

Contribution

It provides a comprehensive comparison of pretrained models for ToD, highlighting their effectiveness and establishing new state-of-the-art results.

Findings

BART and T5 outperform GPT-based models in BLEU and F1 scores

Fine-tuning improves response fluency and accuracy

Models effectively incorporate knowledge to reduce hallucinations

Abstract

The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models. In task-oriented dialogue (ToD) systems, language models can be used for end-to-end training without relying on dialogue state tracking to track the dialogue history but allowing the language models to generate responses according to the context given as input. This paper conducts a comparative study to show the effectiveness and strength of using recent pretrained models for fine-tuning, such as BART and T5, on endto-end ToD systems. The experimental results show substantial performance improvements after language model fine-tuning. The models produce more fluent responses after adding knowledge to the context that guides the model to avoid hallucination and generate accurate entities in the generated responses. Furthermore, we found that BART and T5 outperform GPT-based models in BLEU and F1 scores and achieve state-of-the-art performance in a ToD system.