{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T20:24:57Z","timestamp":1793132697631,"version":"4.5.0"},"reference-count":278,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,2,1]],"date-time":"2021-02-01T00:00:00Z","timestamp":1612137600000},"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-1359275"],"award-info":[{"award-number":["IIS-1359275"]}],"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-1659788"],"award-info":[{"award-number":["IIS-1659788"]}],"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":[[2021,2]]},"DOI":"10.1109\/tnnls.2020.2979670","type":"journal-article","created":{"date-parts":[[2020,4,21]],"date-time":"2020-04-21T16:03:00Z","timestamp":1587484980000},"page":"604-624","source":"Crossref","is-referenced-by-count":1520,"title":["A Survey of the Usages of Deep Learning for Natural Language Processing"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6556-2897","authenticated-orcid":false,"given":"Daniel W.","family":"Otter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian R.","family":"Medina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8765-7018","authenticated-orcid":false,"given":"Jugal K.","family":"Kalita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref274","article-title":"Procedures as a representation for data in a computer program for understanding natural language","author":"winograd","year":"1971"},{"key":"ref277","author":"hennessy","year":"2017","journal-title":"Computer Architecture A Quantitative Approach"},{"key":"ref276","article-title":"A survey of neuromorphic computing and neural networks in hardware","author":"schuman","year":"2017","journal-title":"arXiv 1705 06963"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2094"},{"key":"ref270","doi-asserted-by":"publisher","DOI":"10.1177\/0007650316683926"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271800"},{"key":"ref273","doi-asserted-by":"publisher","DOI":"10.1145\/365153.365168"},{"key":"ref272","article-title":"Natural language input for a computer problem solving system","author":"bobrow","year":"1964"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1145\/234173.234209"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331317"},{"key":"ref174","article-title":"Boosting named entity recognition with neural character embeddings","author":"nogueira dos santos","year":"2015","journal-title":"arXiv 1505 05008"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.3115\/1119176.1119202"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.3115\/1118853.1118857"},{"key":"ref175","first-page":"1986","article-title":"Harem: An advanced ner evaluation contest for portuguese","author":"santos","year":"2006","journal-title":"Proc LREC"},{"key":"ref178","first-page":"142","article-title":"Introduction to the CoNLL-2003 shared task: Language-independent named entity recognition","volume":"4","author":"sang","year":"2003","journal-title":"Proc HLT-NAACL"},{"key":"ref177","article-title":"Named entity recognition with bidirectional LSTM-CNNs","author":"chiu","year":"2015","journal-title":"arXiv 1511 08308"},{"key":"ref168","first-page":"2793","article-title":"Text matching as image recognition","author":"pang","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/2983323.2983769"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref38","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref33","first-page":"493","article-title":"Hierarchical recurrent neural networks for long-term dependencies","author":"el hihi","year":"1996","journal-title":"Proc NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.234"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2011.6163930"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2011.5947611"},{"key":"ref267","article-title":"Google’s multilingual neural machine translation system: Enabling zero-shot translation","author":"johnson","year":"2016","journal-title":"arXiv 1611 04558"},{"key":"ref37","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"chung","year":"2014","journal-title":"arXiv 1412 3555"},{"key":"ref268","author":"jurafsky","year":"2017","journal-title":"Speech & language processing"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref269","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-015-0347-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref180","first-page":"143","article-title":"Towards robust linguistic analysis using ontonotes","author":"pradhan","year":"2013","journal-title":"Proc CoNLL"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1034"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1017"},{"key":"ref183","first-page":"1638","article-title":"Contextual string embeddings for sequence labeling","author":"akbik","year":"2018","journal-title":"Proc COLING"},{"key":"ref182","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2001","journal-title":"Proc 18th Int Conf Mach Learn"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1008"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159712"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.075"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1276"},{"key":"ref28","author":"fausett","year":"1994","journal-title":"Fundamentals of Neural Networks Architectures Algorithms and Applications"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.3115\/1614049.1614064"},{"key":"ref29","first-page":"3","article-title":"Recurrent neural network based language model","volume":"2","author":"mikolov","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref22","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":"ref21","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1062"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00364149"},{"key":"ref23","first-page":"2335","article-title":"Relation classification via convolutional deep neural network","author":"zeng","year":"2014","journal-title":"Proc COLING"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1145\/2601069"},{"key":"ref26","first-page":"801","article-title":"Dynamic pooling and unfolding recursive autoencoders for paraphrase detection","author":"socher","year":"2011","journal-title":"Proc NIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1996.548916"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2014.09.005"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.659013"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S18-2023"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00152"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1129"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2098"},{"key":"ref150","first-page":"996","article-title":"Inference is everything: Recasting semantic resources into a unified evaluation framework","volume":"1","author":"white","year":"2017","journal-title":"Proc IJCNLP"},{"key":"ref152","first-page":"777","article-title":"Resolving complex cases of definite pronouns: The winograd schema challenge","author":"rahman","year":"2012","journal-title":"Proc Joint EMNLP CoNLL"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2067"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.3115\/1072228.1072378"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2082"},{"key":"ref148","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","author":"williams","year":"2017","journal-title":"arXiv 1704 05426"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5301"},{"key":"ref59","article-title":"Network in network","author":"lin","year":"2013","journal-title":"arXiv 1312 4400"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1123"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1442"},{"key":"ref56","article-title":"Frustratingly short attention spans in neural language modeling","author":"daniluk","year":"2017","journal-title":"arXiv 1702 04521"},{"key":"ref55","article-title":"One billion word benchmark for measuring progress in statistical language modeling","author":"chelba","year":"2013","journal-title":"arXiv 1312 3005"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21236\/ADA273556"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2000.0156"},{"key":"ref52","article-title":"Evaluation metrics for language models","author":"chen","year":"2008"},{"key":"ref40","article-title":"A deep reinforced model for abstractive summarization","author":"paulus","year":"2017","journal-title":"arXiv 1705 04304"},{"key":"ref167","first-page":"1367","article-title":"A deep architecture for matching short texts","author":"lu","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1145\/2567948.2577348"},{"key":"ref165","first-page":"2333","article-title":"Learning deep structured semantic models for Web search using clickthrough data","author":"huang","year":"2013","journal-title":"Proc ACM CIKM"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3082062"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2754499"},{"key":"ref160","doi-asserted-by":"crossref","first-page":"722","DOI":"10.1007\/978-3-540-76298-0_52","article-title":"DBpedia: A nucleus for a Web of open data","author":"auer","year":"2007","journal-title":"The Semantic Web"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553486"},{"key":"ref3","first-page":"1337","article-title":"Deep learning with cots HPC systems","author":"coates","year":"2013","journal-title":"Proc ICML"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref5","volume":"1","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref8","first-page":"1237","article-title":"Flexible, high performance convolutional neural networks for image classification","volume":"22","author":"ciresan","year":"2011","journal-title":"Proc IJCAI"},{"key":"ref49","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref157","article-title":"Natural language multitasking: Analyzing and improving syntactic saliency of hidden representations","author":"brunner","year":"2018","journal-title":"arXiv 1801 06024"},{"key":"ref158","first-page":"79","article-title":"Europarl: A parallel corpus for statistical machine translation","volume":"5","author":"koehn","year":"2005","journal-title":"Proc MT Summit"},{"key":"ref9","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"collobert","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref46","article-title":"Highway networks","author":"kumar srivastava","year":"2015","journal-title":"arXiv 1505 00387"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","author":"jurafsky","year":"2000","journal-title":"Speech & language processing"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref42","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1018"},{"key":"ref44","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref73","article-title":"Stochastic answer networks for machine reading comprehension","author":"liu","year":"2017","journal-title":"arXiv 1712 03556"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1441"},{"key":"ref71","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1202"},{"key":"ref76","first-page":"104","article-title":"Better word representations with recursive neural networks for morphology","author":"luong","year":"2013","journal-title":"Proc CoNLL"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/371920.372094"},{"key":"ref74","article-title":"Stochastic answer networks for natural language inference","author":"liu","year":"2018","journal-title":"arXiv 1804 07888"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1334"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/1187415.1187418"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1080\/01690969108406936"},{"key":"ref60","first-page":"2741","article-title":"Character-aware neural language models","author":"kim","year":"2016","journal-title":"Proc AAAI"},{"key":"ref62","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014","journal-title":"arXiv 1409 2329"},{"key":"ref61","first-page":"1899","article-title":"Compositional morphology for word representations and language modelling","author":"botha","year":"2014","journal-title":"Proc ICML"},{"key":"ref63","article-title":"Exploring the limits of language modeling","author":"jozefowicz","year":"2016","journal-title":"arXiv 1602 02410"},{"key":"ref64","article-title":"Document context language models","author":"ji","year":"2015","journal-title":"arXiv 1511 03962"},{"key":"ref65","first-page":"1428","article-title":"Sparse non-negative matrix language modeling for skip-grams","author":"shazeer","year":"2015","journal-title":"Proc INTERSPEECH"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7179001"},{"key":"ref67","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv 1301 3781 [cs]"},{"key":"ref68","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"2013","journal-title":"Proc NIPS"},{"key":"ref69","author":"radford","year":"2018","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref197","article-title":"DocBERT: BERT for document classification","author":"adhikari","year":"2019","journal-title":"arXiv 1904 08398"},{"key":"ref198","first-page":"1963","article-title":"Genre identification and the compositional effect of genre in literature","author":"worsham","year":"2018","journal-title":"Proc COLING"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICCNC.2018.8390270"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref194","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref195","article-title":"Information processing in dynamical systems: Foundations of harmony theory","author":"smolensky","year":"1986"},{"key":"ref196","author":"fletcher","year":"2013","journal-title":"Practical Methods of Optimization"},{"key":"ref95","first-page":"455","article-title":"Parsing with compositional vector grammars","volume":"1","author":"socher","year":"2013","journal-title":"Proc ACL"},{"key":"ref94","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"2013","journal-title":"Proc EMNLP"},{"key":"ref190","first-page":"65","article-title":"A bert-based universal model for both within-and cross-sentence clinical temporal relation extraction","author":"lin","year":"2019","journal-title":"Proc Clin NLP Workshop"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.3115\/1697236.1697250"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1104"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.3115\/1613148.1613156"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-016-2401-x"},{"key":"ref91","first-page":"149","article-title":"An efficient algorithm for projective dependency parsing","author":"nivre","year":"2003","journal-title":"Proc Int Workshop Parsing Technol"},{"key":"ref90","first-page":"3847","article-title":"CONLL-UL: Universal morphological lattices for universal dependency parsing","author":"more","year":"2018","journal-title":"Proc 11th Int Conf Lang Resour Eval"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1081"},{"key":"ref99","first-page":"2773","article-title":"Grammar as a foreign Language","author":"vinyals","year":"2015","journal-title":"Proc NIPS"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3986-5_10"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-76626-8_35"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1080"},{"key":"ref81","first-page":"873","article-title":"Improving word representations via global context and multiple word prototypes","volume":"1","author":"huang","year":"2012","journal-title":"Proc ACL"},{"key":"ref84","article-title":"An Arabic–Hebrew parallel corpus of TED talks","author":"cettolo","year":"2016","journal-title":"arXiv 1610 00572"},{"key":"ref83","first-page":"261","article-title":"WIT3: Web inventory of transcribed and translated talks","author":"cettolo","year":"2012","journal-title":"Proc Conf Eur Assoc Mach Transl"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/365628.365657"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1312"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1276"},{"key":"ref86","first-page":"1344","article-title":"Case frame compilation from the Web using high-performance computing","author":"kawahara","year":"2006","journal-title":"Proc LREC"},{"key":"ref87","first-page":"2008","article-title":"Construction of a Japanese relevance-tagged corpus","author":"kawahara","year":"2002","journal-title":"Proc LREC"},{"key":"ref88","first-page":"535","article-title":"Building a diverse document leads corpus annotated with semantic relations","author":"hangyo","year":"2012","journal-title":"Proc Pacific–Asia Conf Lang Inf Comput"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1016"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220238"},{"key":"ref100","first-page":"1","article-title":"Overview of the 2012 shared task on parsing the Web","volume":"59","author":"petrov","year":"2012","journal-title":"Proc Notes 1st Workshop Syntactic Anal Non-Canonical Lang"},{"key":"ref209","first-page":"868","article-title":"Event representations for automated story generation with deep neural nets","author":"martin","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref203","article-title":"Genrating believable poetry in multiple languages using GPT-2","author":"tucker","year":"2019"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1153"},{"key":"ref201","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"radford","year":"2019","journal-title":"OpenAIRE blog"},{"key":"ref202","article-title":"Introducing aspects of creativity in automatic poetry generation","author":"bena","year":"2019","journal-title":"Proc Int Conf NLP"},{"key":"ref207","article-title":"Story generation from sequence of independent short descriptions","author":"jain","year":"2017","journal-title":"arXiv 1707 05501"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1505"},{"key":"ref205","article-title":"Neural joke generation","author":"ren","year":"2017"},{"key":"ref206","article-title":"Knowledge amalgam: Generating jokes and quotes together","author":"chippada","year":"2018","journal-title":"arXiv 1806 04387"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1462"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1204"},{"key":"ref212","first-page":"180","article-title":"Hierarchical text generation using an outline","author":"drissi","year":"2018","journal-title":"Proc Int Conf NLP"},{"key":"ref213","article-title":"Hierarchically structured reinforcement learning for topically coherent visual story generation","author":"huang","year":"2018","journal-title":"arXiv 1805 08191"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1082"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1107"},{"key":"ref216","first-page":"3155","article-title":"Adversarial ranking for language generation","author":"lin","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref217","article-title":"Controllable neural story plot generation via reinforcement learning","author":"tambwekar","year":"2018","journal-title":"arXiv 1809 10736"},{"key":"ref218","first-page":"4006","article-title":"Adversarial feature matching for text generation","volume":"70","author":"zhang","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref219","first-page":"4666","article-title":"Adversarial text generation via feature-mover’s distance","author":"chen","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref220","first-page":"5141","article-title":"Long text generation via adversarial training with leaked information","author":"guo","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref222","article-title":"Tutorial on variational autoencoders","author":"doersch","year":"2016","journal-title":"arXiv 1606 05908"},{"key":"ref221","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5477"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1169"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1264"},{"key":"ref226","article-title":"The curious case of neural text degeneration","author":"holtzman","year":"2019","journal-title":"arXiv 1904 09751"},{"key":"ref225","article-title":"Topic-guided variational autoencoders for text generation","author":"wang","year":"2019","journal-title":"arXiv 1903 07137"},{"key":"ref224","first-page":"1587","article-title":"Toward controlled generation of text","volume":"70","author":"hu","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref223","first-page":"3295","article-title":"A hierarchical latent variable encoder-decoder model for generating dialogues","author":"serban","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref127","article-title":"Universal dependency parsing with a general transition-based DAG parser","author":"hershcovich","year":"2018","journal-title":"arXiv 1808 09354"},{"key":"ref126","first-page":"1","article-title":"CoNLL 2018 shared task: Multilingual parsing from raw text to universal dependencies","author":"zeman","year":"2018","journal-title":"Proc CoNLL Shared Task Multilingual Parsing Raw Text Universal Dependencies"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18111-0_1"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2008"},{"key":"ref129","article-title":"Universal dependency parsing from scratch","author":"qi","year":"2019","journal-title":"arXiv 1901 10457"},{"key":"ref128","first-page":"248","article-title":"AntNLP at CoNLL 2018 shared task: A graph-based parser for universal dependency parsing","author":"ji","year":"2018","journal-title":"Proc CoNLL Shared Task Multilingual Parsing Raw Text Universal Dependencies"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1088"},{"key":"ref133","first-page":"2042","article-title":"Convolutional neural network architectures for matching natural language sentences","author":"hu","year":"2014","journal-title":"Proc NIPS"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5363-6"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1080\/00437956.1954.11659520"},{"key":"ref232","first-page":"1","article-title":"Abstractive summarization using attentive neural techniques","author":"krantz","year":"2018","journal-title":"Proc Int Conf NLP"},{"key":"ref233","article-title":"Sequence level training with recurrent neural networks","author":"ranzato","year":"2015","journal-title":"arXiv 1511 06732"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-018-1566-y"},{"key":"ref239","article-title":"End-to-End open-domain question answering with BERTserini","author":"yang","year":"2019","journal-title":"arXiv 1902 01718"},{"key":"ref238","article-title":"Discovering objects and their relations from entangled scene representations","author":"raposo","year":"2017","journal-title":"arXiv 1702 05068"},{"key":"ref235","article-title":"Pretraining-based natural language generation for text summarization","author":"zhang","year":"2019","journal-title":"arXiv 1902 09243"},{"key":"ref234","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"arXiv 1705 03122"},{"key":"ref237","first-page":"4974","article-title":"A simple neural network module for relational reasoning","volume":"2017","author":"santoro","year":"0","journal-title":"Proc NIPS"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1026"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220406"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1091"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/S14-2001"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1181"},{"key":"ref139","first-page":"385","article-title":"SemEval-2012 task 6: A pilot on semantic textual similarity","volume":"1","author":"agirre","year":"2012","journal-title":"Proc Joint Conf Lexical Comput Semantics"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1108"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/S14-2010"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"ref143","first-page":"22","article-title":"What is the jeopardy model? A quasi-synchronous grammar for QA","author":"wang","year":"2007","journal-title":"Proc Joint EMNLP CoNLL"},{"key":"ref144","first-page":"1188","article-title":"Distributed representations of sentences and documents","author":"le","year":"2014","journal-title":"Proc ICML"},{"key":"ref2","article-title":"Natural language processing","author":"liddy","year":"2001","journal-title":"Encyclopedia of Library and Information Science"},{"key":"ref145","article-title":"Twitter sentiment classification using distant supervision","volume":"1","author":"go","year":"2009"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-585-35958-8_1"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.3115\/1626431.1626476"},{"key":"ref242","first-page":"1700","article-title":"Recurrent continuous translation models","author":"kalchbrenner","year":"2013","journal-title":"Proc EMNLP"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref240","first-page":"1071","article-title":"Continuous space translation models for phrase-based statistical machine translation","author":"schwenk","year":"2012","journal-title":"Proc COLING"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-3017"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1151"},{"key":"ref246","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":"ref245","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc NIPS"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-4012"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.3115\/1608858.1608859"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1033"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1043"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1032"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1117"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1082"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.3115\/1596324.1596352"},{"key":"ref102","article-title":"Transition-based dependency parsing using recursive neural networks","author":"stenetorp","year":"2013","journal-title":"Proc Deep Learn Workshop Conf Neural Inf Process Syst (NIPS)"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1231"},{"key":"ref112","first-page":"5561","article-title":"A neural transition-based approach for semantic dependency graph parsing","author":"wang","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1017\/S135132490400364X"},{"key":"ref250","article-title":"Linguistic input features improve neural machine translation","author":"sennrich","year":"2016","journal-title":"arXiv 1606 02892"},{"key":"ref251","article-title":"Weighted transformer network for machine translation","author":"ahmed","year":"2017","journal-title":"arXiv 1711 02132"},{"key":"ref254","article-title":"Parallel attention mechanisms in neural machine translation","author":"richard medina","year":"2018","journal-title":"arXiv 1810 12427"},{"key":"ref255","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc ACL"},{"key":"ref252","article-title":"Gradient flow in recurrent nets: The difficulty of learning long-term dependencies","author":"hochreiter","year":"2001","journal-title":"A Field Guide to Dynamical Recurrent Neural Networks"},{"key":"ref253","first-page":"2","article-title":"Report on the 11th IWSLT evaluation campaign, IWSLT 2014","author":"cettolo","year":"2014","journal-title":"Proc Int Workshop Spoken Lang Transl"},{"key":"ref257","article-title":"Cross-lingual language model pretraining","author":"lample","year":"2019","journal-title":"arXiv 1901 07291"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1633"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3203"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.2200\/S00762ED1V01Y201703HLT037"},{"key":"ref258","article-title":"The best of both worlds: Combining recent advances in neural machine translation","author":"xu chen","year":"2018","journal-title":"arXiv 1804 09849"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_r_00312"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1160"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2105"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(82)90024-3"},{"key":"ref18","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1024"},{"key":"ref19","article-title":"One weird trick for parallelizing convolutional neural networks","author":"krizhevsky","year":"2014","journal-title":"arXiv 1404 5997"},{"key":"ref114","article-title":"Improved semantic representations from tree-structured long short-term memory networks","author":"sheng tai","year":"2015","journal-title":"arXiv 1503 00075"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2006"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S16-1167"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S15-2153"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1257"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2025"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-2077"},{"key":"ref123","first-page":"4929","article-title":"Deep semantic role labeling with self-attention","author":"tan","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-3204"},{"key":"ref261","first-page":"596","article-title":"Modeling coherence for neural machine translation with dynamic and topic caches","author":"kuang","year":"2018","journal-title":"Proc COLING"},{"key":"ref262","article-title":"Addressing the rare word problem in neural machine translation","author":"luong","year":"2014","journal-title":"arXiv 1410 8206"},{"key":"ref263","article-title":"Neural machine translation of rare words with subword units","author":"sennrich","year":"2015","journal-title":"arXiv 1508 07909"},{"key":"ref264","article-title":"Lost in translation: Analysis of information loss during machine translation between polysynthetic and fusional languages","author":"mager","year":"2018","journal-title":"arXiv 1807 00286"},{"key":"ref265","article-title":"Analyzing uncertainty in neural machine translation","author":"ott","year":"2018","journal-title":"arXiv 1803 00047"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6314"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9346113\/9075398-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9346113\/09075398.pdf?arnumber=9075398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T10:53:10Z","timestamp":1652179990000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9075398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2]]},"references-count":278,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2979670","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2]]}}}