{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:56:32Z","timestamp":1761396992016,"version":"3.33.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832293","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"849-856","source":"Crossref","is-referenced-by-count":1,"title":["Taming NLU Noise: Student-Teacher Learning for Robust Dialogue Policy"],"prefix":"10.1109","author":[{"given":"Mahdin","family":"Rohmatillah","sequence":"first","affiliation":[{"name":"Universitas Brawijaya,Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Tzung","family":"Chien","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv:1707.06347"},{"article-title":"Learning robust rewards with adverserial inverse reinforcement learning","volume-title":"Proc. of International Conference on Learning Representations","author":"Fu","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482333"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1010"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3235202"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446138"},{"key":"ref7","first-page":"670","article-title":"Promoting mental self-disclosure in a spoken dialogue system","volume-title":"Proc. of Annual Conference of International Speech Communication Association","author":"Rohmatillah"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000132"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000944"},{"article-title":"Learning robust dialog policies in noisy environments","volume-title":"Proc. of Workshop on Conversational AI in Neural Information Processing Systems","author":"Fazel-Zarandi","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6516"},{"key":"ref12","article-title":"Investigation of error simulation techniques for learning dialog policies for conversational error recovery","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Fazel-Zarandi"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1547"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5555\/3016100.3016191"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","article-title":"Multiwoz 2.1: Multi-domain dialogue state corrections and state tracking baselines","author":"Eric","year":"2019","journal-title":"arXiv preprint arXiv:1907.01669"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.19"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538677.003.0006"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.sigdial-1.10"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.32"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11946"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746696"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094860"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/116.20240024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1800"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. of International Conference on Learning Representations","author":"Schulman","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00314"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6394"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688234"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-3011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960692"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832293.pdf?arnumber=10832293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:11:07Z","timestamp":1737101467000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832293","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}