{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T22:52:53Z","timestamp":1772837573732,"version":"3.50.1"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 108-2221-E-006-103-MY3"],"award-info":[{"award-number":["MOST 108-2221-E-006-103-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/taslp.2019.2949687","type":"journal-article","created":{"date-parts":[[2019,10,25]],"date-time":"2019-10-25T20:10:30Z","timestamp":1572034230000},"page":"131-143","source":"Crossref","is-referenced-by-count":13,"title":["Attention-Based Response Generation Using Parallel Double Q-Learning for Dialog Policy Decision in a Conversational System"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0633-774X","authenticated-orcid":false,"given":"Ming-Hsiang","family":"Su","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-2123","authenticated-orcid":false,"given":"Chung-Hsien","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang-Yu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"177","article-title":"The lexical knowledge and semantic representation of E-HowNet","volume":"15","author":"lin","year":"2013","journal-title":"Contemporary Linguistics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/981210.981231"},{"key":"ref33","article-title":"End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning","author":"williams","year":"2016","journal-title":"arXiv 1606 01269"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1065"},{"key":"ref31","first-page":"5141","article-title":"Long text generation via adversarial training with leaked information","author":"guo","year":"2018","journal-title":"Proc 32th AAAI Conf Artif Intell"},{"key":"ref30","first-page":"4006","article-title":"Adversarial feature matching for text generation","author":"zhang","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"3:1?3:24","article-title":"Response selection and automatic message-response expansion in retrieval-based QA systems using semantic dependency pair model","volume":"18","author":"su","year":"2019","journal-title":"ACM Trans Asian Low-Resource Lang Inf Process"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/1119250.1119276"},{"key":"ref35","first-page":"85","article-title":"The CKIP Chinese Treebank: Guidelines for annotation","author":"chen","year":"1999","journal-title":"Proc ATALA Workshop–Treebanks"},{"key":"ref34","article-title":"End-to-end optimization of task-oriented dialogue model with deep reinforcement learning","author":"liu","year":"2017","journal-title":"arXiv 1711 10712"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2904058"},{"key":"ref40","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc 26th Int Conf Adv Neural Inf Process Syst"},{"key":"ref11","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref14","article-title":"Universal sentence encoder","author":"cer","year":"2018","journal-title":"arXiv 1803 11175"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/APPEEC.2018.8566471"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1318"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/35021BIGCOMP.2015.7072837"},{"key":"ref18","first-page":"78","article-title":"Acquisition and use of long-term memory for personalized dialog systems","author":"kim","year":"2014","journal-title":"Proc Int Workshop Multimodal Anal Enabling Artif Agents Human-Mach Interact"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"ref28","article-title":"A neural conversational model","author":"vinyals","year":"0","journal-title":"Proc ICML Deep Learn Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1525\/aa.1968.70.6.02a00030"},{"key":"ref27","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3166054.3166058"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461494"},{"key":"ref29","first-page":"2852","article-title":"SeqGAN: Sequence generative adversarial nets with policy gradient","author":"yu","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1300"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2010.58"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1186\/s13636-017-0107-3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICITEED.2014.7007894"},{"key":"ref1","first-page":"3:1?3:24","article-title":"Response selection and automatic message-response expansion in retrieval-based QA systems using semantic dependency pair model","volume":"18","author":"su","year":"2018","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"key":"ref46","article-title":"Jieba: Chinese word segmentation tool","author":"sun","year":"2019"},{"key":"ref20","first-page":"109","article-title":"Simpleds: A simple deep reinforcement learning dialogue system","author":"cuay\u00e1huitl","year":"2016","journal-title":"Dialog with Robots"},{"key":"ref45","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1237"},{"key":"ref47","article-title":"Chinese Gigaword","author":"graff","year":"2003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/589"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/981923.981945"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1961189.1961199"},{"key":"ref23","first-page":"2094","article-title":"Deep reinforcement learning with double Q-Learning","volume":"2","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref26","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref43","first-page":"47:1?47:9","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"Proc Deep Learn Represent Learn Workshop"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8938144\/08883052.pdf?arnumber=8883052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:30:51Z","timestamp":1651080651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8883052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/taslp.2019.2949687","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}