Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Low-Resource Knowledge-Grounded Dialogue Generation

About

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.

Xueliang Zhao, Wei Wu, Chongyang Tao, Can Xu, Dongyan Zhao, Rui Yan• 2020

Related benchmarks

TaskDatasetResultRank
Dialogue GenerationWizard of Wikipedia (WoW) Seen (test)
BLEU-121.8
13
Dialogue GenerationCMU-DoG (test)
BLEU-115
13
Knowledge-Grounded Dialogue GenerationWizard of Wikipedia unseen (test)
BLEU-120.7
11
Showing 3 of 3 rows

Other info

Follow for update