Learning to Express in Knowledge-Grounded Conversation
Xueliang Zhao, Tingchen Fu, Chongyang Tao, Wei Wu, Dongyan Zhao, Rui Yan
Abstract
Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a response with proper knowledge, yet neglect that the same knowledge could be expressed differently by speakers even under the same context. In this work, we mainly consider two aspects of knowledge expression, namely the structure of the response and style of the content in each part. We therefore introduce two sequential latent variables to represent the structure and the content style respectively. We propose a segmentation-based generation model and optimize the model by a variational approach to discover the underlying pattern of knowledge expression in a response. Evaluation results on two benchmarks indicate that our model can learn the structure style defined by a few examples and generate responses in desired content style.
BibTeX
@inproceedings{zhao-etal-2022-learning-express,
title = "Learning to Express in Knowledge-Grounded Conversation",
author = "Zhao, Xueliang and
Fu, Tingchen and
Tao, Chongyang and
Wu, Wei and
Zhao, Dongyan and
Yan, Rui",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.164/",
doi = "10.18653/v1/2022.naacl-main.164",
pages = "2258--2273"
}