Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

09/28/2020
by   Andrea Madotto, et al.
4

Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests. Modularized systems rely on DST to interact with the KB, which is expensive in terms of annotation and inference time. End-to-end systems use the KB directly as input, but they cannot scale when the KB is larger than a few hundred entries. In this paper, we propose a method to embed the KB, of any size, directly into the model parameters. The resulting model does not require any DST or template responses, nor the KB as input, and it can dynamically update its KB via fine-tuning. We evaluate our solution in five task-oriented dialogue datasets with small, medium, and large KB size. Our experiments show that end-to-end models can effectively embed knowledge bases in their parameters and achieve competitive performance in all evaluated datasets.

READ FULL TEXT

page 14

page 17

10/12/2020

Dynamic Memory Enhanced Transformer for End-to-end Task-Oriented Dialogue System

Recent studies try to build task-oriented dialogue system in an end-to-e...
11/29/2017

End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning

In this paper, we present a neural network based task-oriented dialogue ...
01/21/2022

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

The recent development of language models has shown promising results by...
10/15/2021

Few-Shot Bot: Prompt-Based Learning for Dialogue Systems

Learning to converse using only a few examples is a great challenge in c...
05/15/2017

Key-Value Retrieval Networks for Task-Oriented Dialogue

Neural task-oriented dialogue systems often struggle to smoothly interfa...
04/15/2016

A Network-based End-to-End Trainable Task-oriented Dialogue System

Teaching machines to accomplish tasks by conversing naturally with human...
02/27/2021

A Simple But Effective Approach to n-shot Task-Oriented Dialogue Augmentation

The collection and annotation of task-oriented conversational data is a ...