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

01/21/2022
by   Vinsen Marselino Andreas, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/11/2022

Building a Personalized Dialogue System with Prompt-Tuning

Dialogue systems without consistent responses are not fascinating. In th...
research
10/15/2020

Pretrained Language Models for Dialogue Generation with Multiple Input Sources

Large-scale pretrained language models have achieved outstanding perform...
research
02/12/2023

Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue

With the power of large pretrained language models, various research wor...
research
07/30/2023

User-Controlled Knowledge Fusion in Large Language Models: Balancing Creativity and Hallucination

In modern dialogue systems, the use of Large Language Models (LLMs) has ...
research
06/26/2023

How About Kind of Generating Hedges using End-to-End Neural Models?

Hedging is a strategy for softening the impact of a statement in convers...
research
07/12/2022

PLM-ICD: Automatic ICD Coding with Pretrained Language Models

Automatically classifying electronic health records (EHRs) into diagnost...
research
08/15/2022

Efficient Task-Oriented Dialogue Systems with Response Selection as an Auxiliary Task

The adoption of pre-trained language models in task-oriented dialogue sy...

Please sign up or login with your details

Forgot password? Click here to reset