Low-Resource Knowledge-Grounded Dialogue Generation

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

117 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Dialogue & Conversational AI, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Minlie Huang
  2. Pascale Fung
  3. Andrea Madotto
  4. Dongyan Zhao
  5. Jianfeng Gao
  6. Dan Su
  7. Zihan Liu
  8. Wei Wu

In Dialogue & Conversational AI

  1. Andrea Madotto
  2. Dongyan Zhao
  3. Rui Yan
  4. Zihan Liu
  5. Minlie Huang
  6. Can Xu
  7. Chongyang Tao

In Natural Language Generation

  1. Dan Su
  2. Ruslan Salakhutdinov
  3. Alan W. Black
  4. Minlie Huang
  5. Shrimai Prabhumoye
  6. Heiga Zen
  7. Junichi Yamagishi

Citations in the corpus