{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T23:31:02Z","timestamp":1768001462126,"version":"3.49.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["SCHW 623\/7-1"],"award-info":[{"award-number":["SCHW 623\/7-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3110911","type":"journal-article","created":{"date-parts":[[2021,9,7]],"date-time":"2021-09-07T19:31:01Z","timestamp":1631043061000},"page":"125269-125299","source":"Crossref","is-referenced-by-count":15,"title":["Next-Generation Neural Networks: Capsule Networks With Routing-by-Agreement for Text Classification"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8182-6781","authenticated-orcid":false,"given":"Nikolai A. K.","family":"Steur","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5118-0812","authenticated-orcid":false,"given":"Friedhelm","family":"Schwenker","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/1060745.1060764"},{"key":"ref72","year":"2021","journal-title":"TensorFlow Datasets a Collection of Ready-to-Use Datasets"},{"key":"ref71","first-page":"142","article-title":"Learning word vectors for sentiment analysis","author":"maas","year":"2011","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ASONAM.2016.7752207"},{"key":"ref76","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/1062745.1062778"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref33","first-page":"860","author":"russell","year":"2016","journal-title":"Artificial Intelligence A Modern Approach"},{"key":"ref32","first-page":"141","author":"g\u00e9ron","year":"2019","journal-title":"Hands-On Machine Learning with Scikit-Learn Keras and TensorFlow Concepts Tools and Techniques to Build Intelligent Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref30","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume":"1","author":"macqueen","year":"1967","journal-title":"Proc 5th Berkeley Symp Math Statist Probab"},{"key":"ref37","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"arXiv 1511 07122"},{"key":"ref36","first-page":"27","author":"manning","year":"2009","journal-title":"An Introduction to Information Retrieval"},{"key":"ref35","first-page":"41","author":"zheng","year":"2018","journal-title":"Feature Engineering for Machine Learning Principles and Techniques for Data Scientists"},{"key":"ref34","first-page":"270","author":"davidson","year":"2009","journal-title":"Econometric Theory and Methods"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1104"},{"key":"ref61","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume":"28","author":"zhang","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref63","first-page":"3079","article-title":"Semi-supervised sequence learning","author":"dai","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref28","first-page":"259","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref27","first-page":"45","author":"theodoridis","year":"2009","journal-title":"Pattern Recognition"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"},{"key":"ref66","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst (NIPS)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1126\/science.220.4598.671"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1218990"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2067"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_6"},{"key":"ref1","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1486"},{"key":"ref22","article-title":"A capsule network-based embedding model for knowledge graph completion and search personalization","author":"nguyen","year":"2018","journal-title":"arXiv 1808 04122"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1560"},{"key":"ref24","first-page":"9","article-title":"Introduction to machine learning: An early draft of a proposed textbook","author":"nilsson","year":"2005","journal-title":"Draft of Notes for a Standford course on Machine Learning"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2019.01631"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1977.tb01600.x"},{"key":"ref25","first-page":"21","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref50","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"2","author":"mikolov","year":"2013","journal-title":"Proc 26th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1108\/eb026526"},{"key":"ref59","first-page":"2873","article-title":"Recurrent neural network for text classification with multi-task learning","author":"liu","year":"2016","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852406"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ITOEC49072.2020.9141747"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0026683"},{"key":"ref55","first-page":"1871","article-title":"LIBLINEAR: A library for large linear classification","volume":"9","author":"fan","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref54","first-page":"41","article-title":"A comparison of event models for naive Bayes text classification","author":"mccallum","year":"1998","journal-title":"Proc AAAI Workshop Learn Text Categorization"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-17316-5_8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2068"},{"key":"ref10","article-title":"Text classification using capsules","author":"kim","year":"2018","journal-title":"arXiv 1808 03976"},{"key":"ref11","article-title":"Compositional coding capsule network with k-means routing for text classification","author":"ren","year":"2018","journal-title":"arXiv 1810 09177"},{"key":"ref40","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/759"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-2045"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMSNETS.2019.8711379"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04620-z"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207201"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001390"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1052"},{"key":"ref4","first-page":"1","article-title":"Matrix capsules with EM routing","author":"hinton","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref3","article-title":"Dynamic routing between capsules","author":"sabour","year":"2017","journal-title":"arXiv 1710 09829"},{"key":"ref6","first-page":"1","article-title":"Learning capsule networks with images and text","author":"feng","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst (NIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3297097.3297105"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1350"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"64","DOI":"10.36548\/jaicn.2020.2.001","article-title":"Capsule network on font style classification","volume":"2","author":"vijayakumar","year":"2020","journal-title":"J Artif Intell Capsule Netw"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref9","first-page":"98","article-title":"Identifying aggression and toxicity in comments using capsule network","author":"srivastava","year":"2018","journal-title":"Proc 1st Workshop Trolling Aggression Cyberbullying (TRAC)"},{"key":"ref46","first-page":"746","article-title":"Linguistic regularities in continuous space word representations","author":"mikolov","year":"2013","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref48","first-page":"1","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","first-page":"1","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"Proc Deep Learning Symp (NIPS)"},{"key":"ref44","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09530541.pdf?arnumber=9530541","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:30Z","timestamp":1639770930000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9530541\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3110911","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}