{"type":"ScholarlyArticle","title":"Progressive Open-Domain Response Generation with Multiple Controllable Attributes","authors":[{"name":"Haiqin Yang","slug":"haiqin-yang","given":"Haiqin","family":"Yang","affiliation":""},{"name":"Xiaoyuan Yao","slug":"xiaoyuan-yao","given":"Xiaoyuan","family":"Yao","affiliation":""},{"name":"Yiqun Duan","slug":"yiqun-duan","given":"Yiqun","family":"Duan","affiliation":""},{"name":"Jianping Shen","slug":"jianping-shen","given":"Jianping","family":"Shen","affiliation":""},{"name":"Jie Zhong","slug":"jie-zhong","given":"Jie","family":"Zhong","affiliation":""},{"name":"Kun Zhang","slug":"kun-zhang","given":"Kun","family":"Zhang","affiliation":""}],"abstract":"It is desirable to include more controllable attributes to enhance the diversity of generated responses in open-domain dialogue systems.  However, existing methods can generate responses with only one controllable attribute or lack a flexible way to generate them with multiple controllable attributes.  In this paper, we propose a Progressively trained Hierarchical Encoder-Decoder (PHED) to tackle this task.  More specifically, PHED deploys Conditional Variational AutoEncoder (CVAE) on Transformer to include one aspect of attributes at one stage.  A vital characteristic of the CVAE is to separate the latent variables at each stage into two types: a global variable capturing the common semantic features and a specific variable absorbing the attribute information at that stage.  PHED then couples the CVAE latent variables with the Transformer encoder and is trained by minimizing a newly derived ELBO and controlled losses to produce the next stage's input and produce responses as required.  Finally, we conduct extensive evaluations to show that PHED significantly outperforms the state-of-the-art neural generation models and produces more diverse responses as expected.","doi":"10.24963/ijcai.2021/451","url":"https://ijcai.org/proceedings/2021/451","pdf":"https://ijcai.org/proceedings/2021/0451.pdf","markdown":"https://ijcai.org/proceedings/2021/451.md","bibtex":"https://ijcai.org/proceedings/2021/bibtex/451","volume":{"slug":"2021","title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2021","url":"https://ijcai.org/proceedings/2021/","year":2021,"location":"Montreal","dates":"19-27 August 2021","editors":"Prof. Zhi-Hua Zhou","isbn":"978-0-9992411-9-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2021"},"section":"Machine Learning","track":"Main Track","number":451,"pages":{"first":3279,"last":3285},"keywords":["Machine Learning: Learning Generative Models","Natural Language Processing: Dialogue"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}