{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:35:30Z","timestamp":1784090130233,"version":"3.55.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T00:00:00Z","timestamp":1563494400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T00:00:00Z","timestamp":1563494400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2020,4]]},"DOI":"10.1007\/s13042-019-00982-x","type":"journal-article","created":{"date-parts":[[2019,7,19]],"date-time":"2019-07-19T20:02:35Z","timestamp":1563566555000},"page":"751-761","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Combination of loss functions for deep text classification"],"prefix":"10.1007","volume":"11","author":[{"given":"Hamideh","family":"Hajiabadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego","family":"Molla-Aliod","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Reza","family":"Monsefi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hadi Sadoghi","family":"Yazdi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,7,19]]},"reference":[{"issue":"473","key":"982_CR1","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1198\/016214505000000907","volume":"101","author":"PL Bartlett","year":"2006","unstructured":"Bartlett PL, Jordan MI, McAuliffe JD (2006) Convexity, classification, and risk bounds. J Am Stat Assoc 101(473):138\u2013156","journal-title":"J Am Stat Assoc"},{"issue":"Feb","key":"982_CR2","first-page":"1137","volume":"3","author":"Y Bengio","year":"2003","unstructured":"Bengio Y, Ducharme R, Vincent P, Jauvin C (2003) A neural probabilistic language model. J Mach Learn Res 3(Feb):1137\u20131155","journal-title":"J Mach Learn Res"},{"issue":"Sep","key":"982_CR3","first-page":"2015","volume":"9","author":"G Biau","year":"2008","unstructured":"Biau G, Devroye L, Lugosi G (2008) Consistency of random forests and other averaging classifiers. J Mach Learn Res 9(Sep):2015\u20132033","journal-title":"J Mach Learn Res"},{"issue":"2","key":"982_CR4","first-page":"123","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24(2):123\u2013140","journal-title":"Mach Learn"},{"issue":"1","key":"982_CR5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"key":"982_CR6","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.neucom.2017.06.080","volume":"278","author":"L Chen","year":"2017","unstructured":"Chen L, Qu H, Zhao J (2017) Generalized correntropy based deep learning in presence of non-gaussian noises. Neurocomputing 278:41\u201350","journal-title":"Neurocomputing"},{"key":"982_CR7","doi-asserted-by":"crossref","unstructured":"Collobert R, Weston J (2008) A unified architecture for natural language processing: Deep neural networks with multitask learning. In: Proceedings of the 25th international conference on Machine learning. ACM, New York, pp 160\u2013167","DOI":"10.1145\/1390156.1390177"},{"issue":"Aug","key":"982_CR8","first-page":"2493","volume":"12","author":"R Collobert","year":"2011","unstructured":"Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12(Aug):2493\u20132537","journal-title":"J Mach Learn Res"},{"key":"982_CR9","unstructured":"Condorcet MJANC (1955) Sketch for a historical picture of the progress of the human mind"},{"issue":"5","key":"982_CR10","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1109\/PROC.1979.11321","volume":"67","author":"BV Dasarathy","year":"1979","unstructured":"Dasarathy BV, Sheela BV (1979) A composite classifier system design: concepts and methodology. Proc IEEE 67(5):708\u2013713","journal-title":"Proc IEEE"},{"issue":"1","key":"982_CR11","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"P-T De Boer","year":"2005","unstructured":"De Boer P-T, Kroese DP, Mannor S, Rubinstein RY (2005) A tutorial on the cross-entropy method. Ann Oper Res 134(1):19\u201367","journal-title":"Ann Oper Res"},{"key":"982_CR12","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.ijar.2017.10.021","volume":"93","author":"M Dragoni","year":"2018","unstructured":"Dragoni M, Petrucci G (2018) A fuzzy-based strategy for multi-domain sentiment analysis. Int J Approx Reason 93:59\u201373","journal-title":"Int J Approx Reason"},{"key":"982_CR13","unstructured":"Freund Y, Schapire RE et\u00a0al (1996) Experiments with a new boosting algorithm. In: ICML'96 Proceedings of the Thirteenth International Conference on Machine Learning, Bari, Italy, 03\u201306 July 1996. Morgan Kaufmann Publishers, San Francisco, CA, USA, pp 148\u2013156"},{"key":"982_CR14","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970838","volume-title":"Augmented Lagrangian and operator-splitting methods in nonlinear mechanics","author":"R Glowinski","year":"1989","unstructured":"Glowinski R, Le Tallec P (1989) Augmented Lagrangian and operator-splitting methods in nonlinear mechanics, vol 9. SIAM, Philadelphia"},{"key":"982_CR15","unstructured":"Hajiabadi H, Molla-Aliod D, Monsefi R (2017) On extending neural networks with loss ensembles for text classification. arXiv:1711.05170 (preprint)"},{"issue":"4","key":"982_CR16","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1007\/s10489-018-1341-9","volume":"49","author":"Hamideh Hajiabadi","year":"2018","unstructured":"Hajiabadi H, Monsefi R, Yazdi HS (2018) relf: robust regression extended with ensemble loss function. Appl Intell 49(4):1437\u20131450","journal-title":"Applied Intelligence"},{"issue":"10","key":"982_CR17","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1109\/34.58871","volume":"12","author":"LK Hansen","year":"1990","unstructured":"Hansen LK, Salamon P (1990) Neural network ensembles. IEEE Trans Pattern Anal Mach Intell 12(10):993\u20131001","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"982_CR18","doi-asserted-by":"publisher","first-page":"1561","DOI":"10.1109\/TPAMI.2010.220","volume":"33","author":"R He","year":"2011","unstructured":"He R, Zheng W-S, Bao-Gang H (2011) Maximum correntropy criterion for robust face recognition. IEEE Trans Pattern Anal Mach Intell 33(8):1561\u20131576","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"8","key":"982_CR19","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"982_CR20","doi-asserted-by":"crossref","unstructured":"Hu M, Liu B (2004) Mining and summarizing customer reviews. In: Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining, 22 August 2004. ACM, pp 168\u2013177","DOI":"10.1145\/1014052.1014073"},{"key":"982_CR21","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/3-540-45665-1_31","volume-title":"Pattern recognition with support vector machines","author":"HC Kim","year":"2002","unstructured":"Kim HC, Pang S, Je HM, Kim D, Bang SY (2002) Support vector machine ensemble with bagging. Pattern recognition with support vector machines. Springer, New York, pp 397\u2013408"},{"key":"982_CR22","doi-asserted-by":"crossref","unstructured":"Kim Y (2014) Convolutional neural networks for sentence classification. arXiv:1408.5882 (preprint)","DOI":"10.3115\/v1\/D14-1181"},{"key":"982_CR23","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097\u20131105"},{"key":"982_CR24","doi-asserted-by":"crossref","unstructured":"Li X, Roth D (2002) Learning question classifiers. In: Proceedings of the 19th international conference on Computational linguistics, vol 1, 24 August 2002. Association for Computational Linguistics, pp 1\u20137","DOI":"10.3115\/1072228.1072378"},{"key":"982_CR25","unstructured":"Liu W, Pokharel PP, Principe JC (2006) Correntropy: a localized similarity measure. In: The IEEE international joint conference on neural network proceedings, 16 July 2006. IEEE, pp 4919\u20134924"},{"key":"982_CR26","unstructured":"Mandelbaum A, Shalev A (2016) Word embeddings and their use in sentence classification tasks. arXiv:1610.08229 (preprint)"},{"key":"982_CR27","unstructured":"Mannor S, Meir R (2001) Weak learners and improved rates of convergence in boosting. In: Advances in neural information processing systems, pp 280\u2013286"},{"key":"982_CR28","unstructured":"Masnadi-Shirazi H, Vasconcelos N (2009) On the design of loss functions for classification: theory, robustness to outliers, and savageboost. In: Advances in neural information processing systems, pp 1049\u20131056"},{"key":"982_CR29","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111\u20133119"},{"key":"982_CR30","unstructured":"Moore R, DeNero J (2011) L1 and L2 regularization for multiclass hinge loss models. In: Symposium on machine learning in speech and language processing"},{"key":"982_CR31","doi-asserted-by":"crossref","unstructured":"Nocedal J, Wright SJ (2006) Penalty and augmented Lagrangian methods. In: Numerical Optimization, pp 497\u2013528","DOI":"10.1007\/978-0-387-40065-5_17"},{"key":"982_CR32","doi-asserted-by":"crossref","unstructured":"Pang B, Lee L (2005) Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings of the 43rd annual meeting on association for computational linguistics, 25 June 2005. Association for Computational Linguistics, pp 115\u2013124","DOI":"10.3115\/1219840.1219855"},{"key":"982_CR33","unstructured":"Socher R, Perelygin A, Wu J, Chuang J, Manning CD, Ng A, Potts C (2013) Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 conference on empirical methods in natural language processing, pp 1631\u20131642"},{"key":"982_CR34","doi-asserted-by":"crossref","unstructured":"Sundermeyer M, Schl\u00fcter R, Ney H (2012) Lstm neural networks for language modeling. In: Thirteenth annual conference of the international speech communication association","DOI":"10.21437\/Interspeech.2012-65"},{"key":"982_CR35","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104\u20133112"},{"key":"982_CR36","first-page":"131","volume":"2","author":"CH Yu","year":"1977","unstructured":"Yu CH (1977) Exploratory data analysis. Methods 2:131\u2013160","journal-title":"Methods"},{"key":"982_CR37","volume-title":"Statistical learning theory","author":"V Vapnik","year":"1998","unstructured":"Vapnik V (1998) Statistical learning theory. Wiley, New York"},{"key":"982_CR38","doi-asserted-by":"crossref","unstructured":"Wang P, Xu J, Xu B, Liu C, Zhang H, Wang F, Hao H (2015) Semantic clustering and convolutional neural network for short text categorization. In: Proceedings of the 53rd annual meeting of the association for computational Linguistics and the 7th international joint conference on natural language processing (vol 2: short papers), pp 352\u2013357","DOI":"10.3115\/v1\/P15-2058"},{"key":"982_CR39","doi-asserted-by":"crossref","unstructured":"Wang W (2008) Some fundamental issues in ensemble methods. In: IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), 1 June 2008. IEEE, pp 2243\u20132250","DOI":"10.1109\/IJCNN.2008.4634108"},{"key":"982_CR40","unstructured":"Weingessel A, Dimitriadou E, Hornik K (2003) An ensemble method for clustering. In: Proceedings of the 3rd international workshop on distributed statistical computing"},{"issue":"13","key":"982_CR41","doi-asserted-by":"publisher","first-page":"7875","DOI":"10.1007\/s11042-015-2702-6","volume":"75","author":"K Yan","year":"2016","unstructured":"Yan K, Li Z, Zhang C (2016) A new multi-instance multi-label learning approach for image and text classification. Multimed Tools Appl 75(13):7875\u20137890","journal-title":"Multimed Tools Appl"},{"key":"982_CR42","first-page":"818","volume-title":"European conference on computer vision","author":"MD Zeiler","year":"2014","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. European conference on computer vision. Springer, New York, pp 818\u2013833"},{"key":"982_CR43","unstructured":"Zhang Y, Wallace B (2015) A sensitivity analysis of (and practitioners\u2019 guide to) convolutional neural networks for sentence classification. arXiv:1510.03820 (preprint)"},{"key":"982_CR44","doi-asserted-by":"crossref","unstructured":"Zhao L, Mammadov M, Yearwood J (2010) From convex to nonconvex: a loss function analysis for binary classification. In: IEEE International Conference on Data Mining Workshops, 13 December 2010. IEEE, pp 1281\u20131288","DOI":"10.1109\/ICDMW.2010.57"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-019-00982-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13042-019-00982-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-019-00982-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T08:17:35Z","timestamp":1664007455000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13042-019-00982-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,19]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,4]]}},"alternative-id":["982"],"URL":"https:\/\/doi.org\/10.1007\/s13042-019-00982-x","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,19]]},"assertion":[{"value":"5 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}