Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

TL;DR

This paper introduces a novel method to embed large knowledge bases directly into the parameters of task-oriented dialogue models, eliminating the need for separate state tracking and enabling dynamic updates.

Contribution

The proposed approach embeds knowledge bases into model parameters, allowing scalable, end-to-end dialogue systems that do not rely on explicit state tracking or KB input.

Findings

Effective embedding of KBs of various sizes into model parameters.

Achieves competitive performance across multiple dialogue datasets.

Enables dynamic KB updates via fine-tuning.

Abstract

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.