{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T19:23:11Z","timestamp":1790623391755,"version":"4.1.0"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906185"],"award-info":[{"award-number":["61906185"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province of China","doi-asserted-by":"publisher","award":["2019A1515011705"],"award-info":[{"award-number":["2019A1515011705"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Research Platform Project","award":["ZDSYS201802051831427"],"award-info":[{"award-number":["ZDSYS201802051831427"]}]},{"DOI":"10.13039\/501100013289","name":"Shenzhen Institutes of Advanced Technology (SIAT) Innovation Program for Excellent Young Researchers","doi-asserted-by":"publisher","award":["Y8G027"],"award-info":[{"award-number":["Y8G027"]}],"id":[{"id":"10.13039\/501100013289","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/tnnls.2020.2975035","type":"journal-article","created":{"date-parts":[[2020,3,5]],"date-time":"2020-03-05T23:50:40Z","timestamp":1583452240000},"page":"49-62","source":"Crossref","is-referenced-by-count":35,"title":["Multitask Learning and Reinforcement Learning for Personalized Dialog Generation: An Empirical Study"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7345-5071","authenticated-orcid":false,"given":"Min","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenting","family":"Tu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5814-8460","authenticated-orcid":false,"given":"Qiang","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9197-895X","authenticated-orcid":false,"given":"Kai","family":"Lei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc ICML"},{"key":"ref38","volume":"135","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref30","first-page":"605","article-title":"Multi-task learning for speaker-role adaptation in neural conversation models","author":"luan","year":"2017","journal-title":"Proc IJCNLP"},{"key":"ref37","article-title":"Reinforcement learning neural turing machines–revised","author":"zaremba","year":"2015","journal-title":"arXiv 1505 00521"},{"key":"ref36","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013","journal-title":"arXiv 1308 0850 [cs]"},{"key":"ref35","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2012.6424228"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.01.012"},{"key":"ref40","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953251"},{"key":"ref12","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017281"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/609"},{"key":"ref17","article-title":"Generating text with deep reinforcement learning","author":"guo","year":"2015","journal-title":"arXiv 1510 09202"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref19","first-page":"1","article-title":"An actor-critic algorithm for sequence prediction","author":"bahdanau","year":"2017","journal-title":"Proc ICLR"},{"key":"ref28","first-page":"2873","article-title":"Recurrent neural network for text classification with multi-task learning","author":"liu","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1094"},{"key":"ref27","first-page":"1","article-title":"Multi-task sequence to sequence learning","author":"luong","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1152"},{"key":"ref6","first-page":"1","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2016","journal-title":"Proc ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1204"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2073"},{"key":"ref8","first-page":"583","article-title":"Data-driven response generation in social media","author":"ritter","year":"2011","journal-title":"Proc EMNLP"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref2","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"serban","year":"2016","journal-title":"Proc AAAI"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5087\/dad.2018.101"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0598-6"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914723"},{"key":"ref45","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref22","first-page":"5317","article-title":"Personalizing a dialogue system with transfer learning","author":"mo","year":"2017","journal-title":"Proc AAAI"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.10.006"},{"key":"ref42","first-page":"935","article-title":"A dataset for research on short-text conversations","author":"wang","year":"2013","journal-title":"Proc EMNLP"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080706"},{"key":"ref41","article-title":"ADADELTA: An adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975321.71"},{"key":"ref44","first-page":"237","article-title":"News from OPUS—A collection of multilingual parallel corpora with tools and interfaces","author":"tiedemann","year":"2009","journal-title":"Proc NIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1092"},{"key":"ref43","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc NIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9312808\/09025776.pdf?arnumber=9025776","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:00Z","timestamp":1652194380000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9025776\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":45,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2975035","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}