{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T05:52:44Z","timestamp":1743832364432},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/451","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:00:49Z","timestamp":1628665249000},"page":"3279-3285","source":"Crossref","is-referenced-by-count":1,"title":["Progressive Open-Domain Response Generation with Multiple Controllable Attributes"],"prefix":"10.24963","author":[{"given":"Haiqin","family":"Yang","sequence":"first","affiliation":[{"name":"Ping An Life Insurance of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyuan","family":"Yao","sequence":"additional","affiliation":[{"name":"Ping An Life Insurance of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Duan","sequence":"additional","affiliation":[{"name":"Ping An Life Insurance of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianping","family":"Shen","sequence":"additional","affiliation":[{"name":"Ping An Life Insurance of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Ping An Life Insurance of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2021","name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","start":{"date-parts":[[2021,8,19]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T07:03:21Z","timestamp":1628665401000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/451"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/451","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}