2020/02/24 by Xueliang Zhao, Wei Wu, Zhao, Xueliang +9 · 84 citations
Computer Science · #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Data science #Domain (mathematical analysis) #Domain knowledge #FOS: Computer and information sciences #Grounded theory #Knowledge management #Machine learning #Natural Language Processing Techniques #Qualitative research #Resource (disambiguation) #Sociology #Speech and dialogue systems #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.2002.10348
published in arXiv (Cornell University) (Cornell University) · Published in ICLR 2020
arxiv created 2020/02/24 · openalex publication_date 2020/02/24 · arxiv updated 2020/02/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.