{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:18:31Z","timestamp":1775283511443,"version":"3.50.1"},"reference-count":44,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1109\/asru.2017.8268975","type":"proceedings-article","created":{"date-parts":[[2018,1,25]],"date-time":"2018-01-25T16:43:53Z","timestamp":1516898633000},"page":"482-489","source":"Crossref","is-referenced-by-count":26,"title":["Iterative policy learning in end-to-end trainable task-oriented neural dialog models"],"prefix":"10.1109","author":[{"given":"Bing","family":"Liu","sequence":"first","affiliation":[]},{"given":"Ian","family":"Lane","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"4","DOI":"10.5087\/dad.2016.301","article-title":"The dialog state tracking challenge series: A review","volume":"7","author":"williams","year":"2016","journal-title":"Dialogue & Discourse"},{"key":"ref38","article-title":"Machine learning for dialog state tracking: A review","author":"henderson","year":"2015","journal-title":"Proc of The First International Workshop on Machine Learning in Spoken Language Processing"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-8280-2_31"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"893","DOI":"10.21437\/Interspeech.2005-401","article-title":"Learning user simulations for information state update dialogue systems","author":"georgila","year":"2005","journal-title":"InterSpeech"},{"key":"ref31","article-title":"End-to-end lstm-based dialog control optimized with supervised and reinforcement learning","author":"williams","year":"2016","journal-title":"arXiv preprint arXiv 1606 01269"},{"key":"ref30","article-title":"Hybrid code networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning","author":"jason","year":"2017","journal-title":"ACL"},{"key":"ref37","first-page":"442","article-title":"Structured discriminative model for dialog state tracking","author":"lee","year":"0","journal-title":"Proceedings of the SIGDIAL 2013 Conference 2013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4602"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1047"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"2506","DOI":"10.21437\/Interspeech.2017-1326","article-title":"An end-to-end trainable neural network model with belief tracking for task-oriented dialog","author":"liu","year":"2017","journal-title":"InterSpeech"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"ronald","year":"1992","journal-title":"Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3603"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4340"},{"key":"ref13","first-page":"1777","article-title":"Neural belief tracker: Data-driven dialogue state tracking","author":"mrk\u0161i?","year":"2017","journal-title":"ACL"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2282190"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1230"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5518"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1042"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-1326","article-title":"An end-to-end trainable neural network model with belief tracking for task-oriented dialog","author":"liu","year":"2017","journal-title":"InterSpeech"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3601"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2011.09.004"},{"key":"ref4","article-title":"Creating natural dialogs in the carnegie mellon communicator system","author":"alexander","year":"1999","journal-title":"Eurospeech"},{"key":"ref27","article-title":"Learning end-to-end goal-oriented dialog","author":"bordes","year":"2017","journal-title":"ICLRE"},{"key":"ref3","article-title":"A persona-based neural conversation model","author":"jiwei","year":"2016","journal-title":"ACL"},{"key":"ref6","article-title":"Lets go public! taking a spoken dialog system to the real world","author":"antoine","year":"2005","journal-title":"Proc of Interspeech 2005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2008.07-028-R2-05-82"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2006.326785"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2383614"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"ref2","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"iulian","year":"2016","journal-title":"Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI'16)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-312"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1152"},{"key":"ref20","article-title":"End-to-end task-completion neural dialogue systems","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1703 01281"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1175"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000944"},{"key":"ref42","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"ICLRE"},{"key":"ref24","first-page":"8367","article-title":"On-line policy optimisation of bayesian spoken dialogue systems via human interaction","author":"ga\u0161i?","year":"2013","journal-title":"ICASSP"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4337"},{"key":"ref23","article-title":"A user simulator for task-completion dialogues","author":"xiujun","year":"2016","journal-title":"arXiv preprint arXiv 1612 05688"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1233"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref43","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"nitish","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"ref25","article-title":"A neural conversational model","author":"vinyals","year":"2015","journal-title":"ICML"}],"event":{"name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","location":"Okinawa","start":{"date-parts":[[2017,12,16]]},"end":{"date-parts":[[2017,12,20]]}},"container-title":["2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8260578\/8268903\/08268975.pdf?arnumber=8268975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T02:16:37Z","timestamp":1660356997000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8268975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/asru.2017.8268975","relation":{},"subject":[],"published":{"date-parts":[[2017,12]]}}}