Log In Sign Up

Low-Resource Knowledge-Grounded Dialogue Generation

by   Xueliang Zhao, et al.

Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain. Motivated by the challenge in practice, we consider knowledge-grounded dialogue generation under a natural assumption that only limited training examples are available. In such a low-resource setting, we devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model. By this means, the major part of the model can be learned from a large number of ungrounded dialogues and unstructured documents, while the remaining small parameters can be well fitted using the limited training examples. Evaluation results on two benchmarks indicate that with only 1/8 training data, our model can achieve the state-of-the-art performance and generalize well on out-of-domain knowledge.


Multimodal Dialogue Response Generation

Responsing with image has been recognized as an important capability for...

A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation

Neural conversation models have shown great potentials towards generatin...

Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation

Knowledge-grounded dialogue systems are challenging to build due to the ...

Open Domain Dialogue Generation with Latent Images

We consider grounding open domain dialogues with images. Existing work a...

Dual Latent Variable Model for Low-Resource Natural Language Generation in Dialogue Systems

Recent deep learning models have shown improving results to natural lang...

On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?

Knowledge-grounded conversational models are known to suffer from produc...

Low-Resource Response Generation with Template Prior

We study open domain response generation with limited message-response p...