{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:52:37Z","timestamp":1740099157324,"version":"3.37.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319995786"},{"type":"electronic","value":"9783319995793"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-99579-3_49","type":"book-chapter","created":{"date-parts":[[2018,8,24]],"date-time":"2018-08-24T07:36:09Z","timestamp":1535096169000},"page":"470-478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["The Benefit of Document Embedding in Unsupervised Document Classification"],"prefix":"10.1007","author":[{"given":"Jarom\u00edr","family":"Novotn\u00fd","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pavel","family":"Ircing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,25]]},"reference":[{"issue":"3","key":"49_CR1","first-page":"285","volume":"14","author":"K Chinniyan","year":"2017","unstructured":"Chinniyan, K., Gangadharan, S., Sabanaikam, K.: Semantic similarity based web document classification using support vector machine. Int. Arab J. Inf. Technol. (IAJIT) 14(3), 285\u2013292 (2017)","journal-title":"Int. Arab J. Inf. Technol. (IAJIT)"},{"key":"49_CR2","doi-asserted-by":"crossref","unstructured":"Hamdi, A., Voerman, J., Coustaty, M., Joseph, A., d\u2019Andecy, V.P., Ogier, J.M.: Machine learning vs deterministic rule-based system for document stream segmentation. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 5, pp. 77\u201382. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.332"},{"issue":"1","key":"49_CR3","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/s00521-016-2401-x","volume":"29","author":"M Jiang","year":"2018","unstructured":"Jiang, M., et al.: Text classification based on deep belief network and softmax regression. Neural Comput. Appl. 29(1), 61\u201370 (2018)","journal-title":"Neural Comput. Appl."},{"key":"49_CR4","doi-asserted-by":"crossref","unstructured":"Lau, J.H., Baldwin, T.: An empirical evaluation of doc2vec with practical insights into document embedding generation. arXiv preprint arXiv:1607.05368 (2016)","DOI":"10.18653\/v1\/W16-1609"},{"key":"49_CR5","doi-asserted-by":"crossref","unstructured":"Liu, Y., Liu, Z., Chua, T.S., Sun, M.: Topical word embeddings. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 2418\u20132424 (2015)","DOI":"10.1609\/aaai.v29i1.9522"},{"key":"49_CR6","unstructured":"MacQueen, J.: Some methods for classification and analysis of multivariate observations. In: 5-th Berkeley Symposium on Mathematical Statistics and Probability, pp. 281\u2013297 (1967)"},{"key":"49_CR7","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1162\/tacl_a_00140","volume":"3","author":"DQ Nguyen","year":"2015","unstructured":"Nguyen, D.Q., Billingsley, R., Du, L., Johnson, M.: Improving topic models with latent feature word representations. Trans. Assoc. Comput. Linguist. 3, 299\u2013313 (2015)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"49_CR8","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1007\/978-3-319-66429-3_75","volume-title":"Speech and Computer","author":"J Novotn\u00fd","year":"2017","unstructured":"Novotn\u00fd, J., Ircing, P.: Unsupervised document classification and\u00a0topic detection. In: Karpov, A., Potapova, R., Mporas, I. (eds.) SPECOM 2017. LNCS (LNAI), vol. 10458, pp. 748\u2013756. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66429-3_75"},{"key":"49_CR9","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F.: Scikit-learn: machine learning in Python. Journal of Machine Learning Research 12, 2825\u20132830 (2011). http:\/\/scikit-learn.org","journal-title":"Journal of Machine Learning Research"},{"key":"49_CR10","unstructured":"\u0158eh\u016f\u0159ek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, pp. 45\u201350 (2010). https:\/\/radimrehurek.com\/gensim\/"},{"key":"49_CR11","doi-asserted-by":"crossref","unstructured":"Siolas, G., d\u2019Alche Buc, F.: Support vector machines based on a semantic kernel for text categorization. In: IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN), vol. 5, pp. 205\u2013209 (2000)","DOI":"10.1109\/IJCNN.2000.861458"},{"key":"49_CR12","doi-asserted-by":"crossref","unstructured":"Slonim, N., Friedman, N., Tishby, N.: Unsupervised document classification using sequential information maximization. In: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 129\u2013136 (2002)","DOI":"10.1145\/564376.564401"},{"key":"49_CR13","doi-asserted-by":"crossref","unstructured":"Strakov\u00e1, J., Straka, M., Haji\u010d, J.: Open-source tools for morphology, lemmatization, POS tagging and named entity recognition. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp. 13\u201318 (2014)","DOI":"10.3115\/v1\/P14-5003"},{"issue":"2","key":"49_CR14","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s10579-013-9246-z","volume":"48","author":"J \u0160vec","year":"2014","unstructured":"\u0160vec, J., et al.: General framework for mining, processing and storing large amounts of electronic texts for language modeling purposes. Lang. Resour. Eval. 48(2), 227\u2013248 (2014). https:\/\/doi.org\/10.1007\/s10579-013-9246-z","journal-title":"Lang. Resour. Eval."},{"key":"49_CR15","doi-asserted-by":"crossref","unstructured":"Trieu, L.Q., Tran, H.Q., Tran, M.T.: News classification from social media using twitter-based doc2vec model and automatic query expansion. In: Proceedings of the Eighth International Symposium on Information and Communication Technology, pp. 460\u2013467. ACM (2017)","DOI":"10.1145\/3155133.3155206"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99579-3_49","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,30]],"date-time":"2022-08-30T05:00:28Z","timestamp":1661835628000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-99579-3_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319995786","9783319995793"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99579-3_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]}}}