Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation

TL;DR

PLUG is a unified language model that homogenizes heterogeneous knowledge sources for knowledge-grounded dialogue generation, enabling better generalization to unseen topics and tasks with limited training data.

Contribution

The paper introduces PLUG, a pre-trained model that unifies diverse knowledge representations, improving zero-shot and few-shot performance in dialogue generation.

Findings

PLUG achieves comparable results to state-of-the-art in fully-supervised settings.

PLUG significantly outperforms other methods in zero-shot and few-shot scenarios.

The model generalizes well across different knowledge-grounded dialogue tasks.

Abstract

Knowledge-grounded dialogue systems are challenging to build due to the lack of training data and heterogeneous knowledge sources. Existing systems perform poorly on unseen topics due to limited topics covered in the training data. In addition, heterogeneous knowledge sources make it challenging for systems to generalize to other tasks because knowledge sources in different knowledge representations require different knowledge encoders. To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks. PLUG is pre-trained on a dialogue generation task conditioned on a unified essential knowledge representation. It can generalize to different downstream knowledge-grounded dialogue generation tasks with a few training examples. The empirical evaluation on two benchmarks shows that our model generalizes well across different knowledge-grounded tasks. It can achieve comparable performance with state-of-the-art methods under a fully-supervised setting and significantly outperforms other methods in zero-shot and few-shot settings.