{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T08:02:46Z","timestamp":1789632166324,"version":"build-2803163510"},"reference-count":183,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1619028"],"award-info":[{"award-number":["IIS-1619028"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1707498"],"award-info":[{"award-number":["IIS-1707498"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1838730"],"award-info":[{"award-number":["IIS-1838730"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DGE-1545362"],"award-info":[{"award-number":["DGE-1545362"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1633363"],"award-info":[{"award-number":["IIS-1633363"]}],"id":[{"id":"10.13039\/100000001","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":[[2019]]},"DOI":"10.1109\/tnnls.2019.2929141","type":"journal-article","created":{"date-parts":[[2019,8,15]],"date-time":"2019-08-15T19:38:10Z","timestamp":1565897890000},"page":"1-21","source":"Crossref","is-referenced-by-count":108,"title":["Deep Reinforcement Learning for Sequence-to-Sequence Models"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-2542","authenticated-orcid":false,"given":"Yaser","family":"Keneshloo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7604-5665","authenticated-orcid":false,"given":"Tian","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1821-9743","authenticated-orcid":false,"given":"Naren","family":"Ramakrishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2839-3662","authenticated-orcid":false,"given":"Chandan K.","family":"Reddy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1165"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1003"},{"key":"ref174","first-page":"1480","article-title":"Darla: Improving zero-shot transfer in reinforcement learning","author":"higgins","year":"2017","journal-title":"Int Conf Mach Learn"},{"key":"ref173","first-page":"675","author":"keneshloo","year":"2019","journal-title":"Deep Transfer Reinforcement Learning for Text Summarization"},{"key":"ref176","first-page":"2817","article-title":"Cold-start reinforcement learning with softmax policy gradient","author":"ding","year":"2017","journal-title":"Proc NIPS"},{"key":"ref175","first-page":"1723","article-title":"Reward augmented maximum likelihood for neural structured prediction","author":"norouzi","year":"2016","journal-title":"Proc NIPS"},{"key":"ref178","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref177","article-title":"Connecting the dots between MLE and RL for sequence generation","author":"tan","year":"2018","journal-title":"arXiv 1811 09740"},{"key":"ref168","article-title":"Learning to decode for future success","author":"li","year":"2017","journal-title":"arXiv 1701 06549"},{"key":"ref169","first-page":"11","article-title":"Learning to extract coherent summary via deep reinforcement learning","author":"wu","year":"2018","journal-title":"Proc AAAI"},{"key":"ref39","article-title":"An actor-critic algorithm for sequence prediction","author":"bahdanau","year":"2017","journal-title":"Proc ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/606"},{"key":"ref33","first-page":"3155","article-title":"Adversarial ranking for language generation","author":"lin","year":"2017","journal-title":"Proc NIPS"},{"key":"ref32","first-page":"2852","article-title":"SeqGan: Sequence generative adversarial nets with policy gradient","volume":"31","author":"yu","year":"2017","journal-title":"Proc AAAI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2058"},{"key":"ref30","article-title":"How (not) to train your generative model: Scheduled sampling, likelihood, adversary?","author":"husz\u00e1r","year":"2015","journal-title":"arXiv 1511 05101"},{"key":"ref37","first-page":"4006","article-title":"Adversarial feature matching for text generation","author":"zhang","year":"2017","journal-title":"Proc ICML"},{"key":"ref36","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref35","article-title":"Maximum-likelihood augmented discrete generative adversarial networks","author":"che","year":"2017","journal-title":"arXiv 1702 07983"},{"key":"ref34","first-page":"1","article-title":"Long text generation via adversarial training with leaked information","author":"guo","year":"2018","journal-title":"Proc AAAI"},{"key":"ref181","article-title":"Implicit quantile networks for distributional reinforcement learning","author":"dabney","year":"2018","journal-title":"arXiv 1806 06923"},{"key":"ref180","first-page":"1458","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2018","journal-title":"Proc AAAI"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1150"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref28","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv 1511 06732"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref179","first-page":"1433","article-title":"Maximum entropy inverse reinforcement learning","author":"ziebart","year":"2008","journal-title":"Proc AAAI"},{"key":"ref29","first-page":"1","article-title":"Incorporating discriminator in sentence generation: A gibbs sampling method","author":"su","year":"2018","journal-title":"Proc AAAI"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref24","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Workshop on Text Summarization Branches Out"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref26","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K17-1041"},{"key":"ref25","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1076"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1008"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-009-5106-x"},{"key":"ref153","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume":"2016","author":"wang","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref156","first-page":"3024","article-title":"Improving multi-step prediction of learned time series models","author":"venkatraman","year":"2015","journal-title":"Proc AAAI"},{"key":"ref155","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref150","first-page":"2613","article-title":"Double q-learning","author":"hasselt","year":"2010","journal-title":"Proc NIPS"},{"key":"ref152","first-page":"15","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI"},{"key":"ref151","article-title":"Issues in using function approximation for reinforcement learning","author":"thrun","year":"1993","journal-title":"Connectionist Models Summer School"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993306"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref149","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1056"},{"key":"ref58","first-page":"1782","article-title":"Deliberation networks: Sequence generation beyond one-pass decoding","author":"xia","year":"2017","journal-title":"Proc NIPS"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1013"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2027"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1063"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1108"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1101"},{"key":"ref52","article-title":"Neural abstractive text summarization with sequence-to-sequence models","author":"shi","year":"2018","journal-title":"arXiv 1812 02303"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref166","article-title":"Actor-critic sequence training for image captioning","author":"zhang","year":"2017","journal-title":"arXiv 1706 09601"},{"key":"ref165","first-page":"177","article-title":"Decoding with value networks for neural machine translation","author":"he","year":"2017","journal-title":"Proc NIPS"},{"key":"ref164","article-title":"Reinforced mnemonic reader for machine comprehension","author":"hu","year":"2017","journal-title":"arXiv 1705 02798"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462361"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1421"},{"key":"ref4","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref6","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref5","first-page":"193","article-title":"Tensor2tensor for neural machine translation","author":"vaswani","year":"2018","journal-title":"Proc Conf Assoc Mach Transl Amer"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1159"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1158"},{"key":"ref7","first-page":"1","article-title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","author":"cho","year":"2014","journal-title":"Proc EMNLP"},{"key":"ref49","first-page":"4","article-title":"Deep learning for siri’s voice: On-device deep mixture density networks for hybrid unit selection synthesis","volume":"1","author":"team","year":"2017","journal-title":"Mach Learn Appl"},{"key":"ref157","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc NIPS"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/619"},{"key":"ref46","article-title":"Actor-critic based training framework for abstractive summarization","author":"li","year":"2018","journal-title":"arXiv 1803 11070"},{"key":"ref45","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":"ref48","article-title":"Deep reinforcement learning: An overview","author":"li","year":"2017","journal-title":"arXiv 1701 07274"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref42","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914549607"},{"key":"ref43","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3115\/1219840.1219885"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1162\/0891201053630264"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"},{"key":"ref73","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"2014","journal-title":"Proc ICML"},{"key":"ref72","article-title":"Sqlnet: Generating structured queries from natural language without reinforcement learning","author":"xu","year":"2017","journal-title":"arXiv 1711 04436"},{"key":"ref71","author":"zhong","year":"2018","journal-title":"Seq2SQL Generating Structured Queries from Natural Languageusing Reinforcement Learning"},{"key":"ref129","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"2011","journal-title":"Proc NIPS"},{"key":"ref70","first-page":"12","article-title":"Learning end-to-end goal-oriented dialog","author":"bordes","year":"2016","journal-title":"Proc ICLR"},{"key":"ref128","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref76","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014","journal-title":"arXiv 1412 6632"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref74","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014","journal-title":"arXiv 1411 2539"},{"key":"ref75","first-page":"2422","article-title":"Mind’s eye: A recurrent visual representation for image caption generation","author":"chen","year":"2015","journal-title":"Proc CVPR"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref134","article-title":"Reinforcement learning neural Turing machines–revised","author":"zaremba","year":"2015","journal-title":"arXiv 1505 00521"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref131","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc ACL"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref135","first-page":"1000","article-title":"On a connection between importance sampling and the likelihood ratio policy gradient","author":"jie","year":"2010","journal-title":"Proc NIPS"},{"key":"ref138","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"Proc NIPS"},{"key":"ref137","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc ICML"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1170"},{"key":"ref139","first-page":"10","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"jaderberg","year":"2017","journal-title":"Proc ICLR"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-2603"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1096"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref64","first-page":"116","article-title":"Dynamic coattention networks for question answering","author":"xiong","year":"2016","journal-title":"Proc ICLR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref140","first-page":"1","article-title":"The reactor: A sample-efficient actor-critic architecture","author":"gruslys","year":"2018","journal-title":"Proc ICLR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313699"},{"key":"ref141","first-page":"11","article-title":"Sample efficient actor-critic with experience replay","author":"wang","year":"2017","journal-title":"Proc ICLR"},{"key":"ref142","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc NIPS"},{"key":"ref67","article-title":"A neural conversational model","author":"vinyals","year":"2015","journal-title":"arXiv 1506 05869"},{"key":"ref143","article-title":"The mirage of action-dependent baselines in reinforcement learning","author":"tucker","year":"2018","journal-title":"Proc ICLR Workshop"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"ref2","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc NIPS"},{"key":"ref144","first-page":"125","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc ICLR"},{"key":"ref69","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","volume":"16","author":"serban","year":"2016","journal-title":"Proc AAAI"},{"key":"ref1","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref145","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref95","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"2013","journal-title":"Proc EMNLP"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1053"},{"key":"ref94","first-page":"69","article-title":"Deep convolutional neural networks for sentiment analysis of short texts","author":"dos santos","year":"2014","journal-title":"Proc COLING"},{"key":"ref108","article-title":"A simple method for commonsense reasoning","author":"trinh","year":"2018","journal-title":"arXiv 1806 02847"},{"key":"ref93","article-title":"Learning to generate reviews and discovering sentiment","author":"radford","year":"2017","journal-title":"arXiv 1704 01444"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1135"},{"key":"ref92","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1074"},{"key":"ref91","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"Proc NIPS"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1199"},{"key":"ref90","article-title":"Multiple object recognition with visual attention","author":"ba","year":"2014","journal-title":"Arxiv 1412 7755"},{"key":"ref104","first-page":"2526","article-title":"Attention-based convolutional neural network for semantic relation extraction","author":"huang","year":"2016","journal-title":"Proc ICLR"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.3115\/1690219.1690287"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref111","first-page":"355","article-title":"Domain adaptation via pseudo in-domain data selection","author":"axelrod","year":"2011","journal-title":"Proc EMNLP"},{"key":"ref112","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"2015","journal-title":"Proc NIPS"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1091"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1112"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1070"},{"key":"ref97","article-title":"Semantic sentence matching with densely-connected recurrent and co-attentive information","author":"kim","year":"2018","journal-title":"arXiv 1805 11360"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1012"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref13","first-page":"1","article-title":"A deep reinforced model for abstractive summarization","author":"paulus","year":"2018","journal-title":"Proc ICLR"},{"key":"ref14","first-page":"3075","article-title":"Summarunner: A recurrent neural network based sequence model for extractive summarization of documents","author":"nallapati","year":"2017","journal-title":"Proc AAAI"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472618"},{"key":"ref82","first-page":"31","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2014","journal-title":"Proc ICLR"},{"key":"ref118","author":"tiedemann","year":"2018","journal-title":"News from OpusžA Collection of Multilingual Parallel Corpora With Tools and Interfaces 1 Index of Subjects and Terms 13"},{"key":"ref17","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"Proc ICML"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1204"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"ref18","first-page":"195","article-title":"Deep voice: Real-time neural text-to-speech","author":"arik","year":"2017","journal-title":"Proc ICML"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref19","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"2015","author":"xu","year":"2015","journal-title":"Comput Sci"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.276"},{"key":"ref119","article-title":"Evaluating prerequisite qualities for learning end-to-end dialog systems","author":"dodge","year":"2015","journal-title":"arXiv 1511 06931"},{"key":"ref114","first-page":"1","author":"graff","year":"2003","journal-title":"English Gigaword"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1065"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref116","first-page":"784","article-title":"Know what you don’t know: Unanswerable questions for squad","author":"rajpurkar","year":"2018","journal-title":"Proc ACL"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref89","first-page":"54","article-title":"TTS synthesis with bidirectional LSTM based recurrent neural networks","author":"fan","year":"2014","journal-title":"Proc ISCA"},{"key":"ref120","first-page":"76","article-title":"Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs","author":"danescu-niculescu-mizil","year":"2011","journal-title":"Proc Workshop Cogn Model Comput Linguist"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1129"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783381"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref86","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc ICML"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639215"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/6104215\/08801910.pdf?arnumber=8801910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:19:32Z","timestamp":1651079972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8801910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":183,"URL":"https:\/\/doi.org\/10.1109\/tnnls.2019.2929141","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}