{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:03:14Z","timestamp":1748491394691,"version":"3.41.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319195803"},{"type":"electronic","value":"9783319195810"}],"license":[{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,1,1]],"date-time":"2015-01-01T00:00:00Z","timestamp":1420070400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-19581-0_1","type":"book-chapter","created":{"date-parts":[[2015,6,4]],"date-time":"2015-06-04T02:30:20Z","timestamp":1433385020000},"page":"3-18","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Supervised Classification Using Information Extraction"],"prefix":"10.1007","author":[{"given":"Mian","family":"Du","sequence":"first","affiliation":[]},{"given":"Matthew","family":"Pierce","sequence":"additional","affiliation":[]},{"given":"Lidia","family":"Pivovarova","sequence":"additional","affiliation":[]},{"given":"Roman","family":"Yangarber","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,6,4]]},"reference":[{"key":"1_CR1","series-title":"Lecture Notes in Social Networks","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/978-3-7091-0388-3_18","volume-title":"Counterterrorism and Open Source Intelligence","author":"M Atkinson","year":"2011","unstructured":"Atkinson, M., Piskorski, J., van der Goot, E., Yangarber, R.: Multilingual real-time event extraction for border security intelligence gathering. In: Wiil, U.K. (ed.) Counterterrorism and Open Source Intelligence. Lecture Notes in Social Networks, vol. 2, pp. 355\u2013390. Springer, Vienna (2011)"},{"key":"1_CR2","unstructured":"Bekkerman, R., Allan, J.: Using bigrams in text categorization. Technical Report IR-408, Department of Computer Science, University of Massachusetts, Amherst (December 2004)"},{"key":"1_CR3","unstructured":"Cisse, M.M., Usunier, N., Arti, T., Gallinari, P.: Robust bloom filters for large multilabel classification tasks. In: Advances in Neural Information Processing Systems, pp. 1851\u20131859 (2013)"},{"key":"1_CR4","first-page":"1891","volume":"13","author":"K Crammer","year":"2012","unstructured":"Crammer, K., Dredze, M., Pereira, F.: Confidence-weighted linear classification for text categorization. J. Mach. Learn. Res. 13, 1891\u20131926 (2012)","journal-title":"J. Mach. Learn. Res."},{"issue":"6","key":"1_CR5","doi-asserted-by":"crossref","first-page":"843","DOI":"10.3233\/IDA-2011-0499","volume":"15","author":"S Dendamrongvit","year":"2011","unstructured":"Dendamrongvit, S., Vateekul, P., Kubat, M.: Irrelevant attributes and imbalanced classes in multi-label text-categorization domains. Intell. Data Anal. 15(6), 843\u2013859 (2011)","journal-title":"Intell. Data Anal."},{"key":"1_CR6","unstructured":"Dredze, M., McNamee, P., Rao, D., Gerber, A., Finin, T.: Entity disambiguation for knowledge base population. In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 277\u2013285. Association for Computational Linguistics (2010)"},{"key":"1_CR7","unstructured":"Du, M., Kangasharju, J., Karkulahti, O., Pivovarova, L., Yangarber, R.: Combined analysis of news and Twitter messages. In: Joint Workshop on NLP&LOD and SWAIE: Semantic Web, Linked Open Data and Information Extraction, pp. 41\u201348 (2013)"},{"key":"1_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/978-3-319-11397-5_11","volume-title":"Statistical Language and Speech Processing","author":"M Du","year":"2014","unstructured":"Du, M., Pierce, M., Pivovarova, L., Yangarber, R.: Supervised classification using balanced training. In: Besacier, L., Dediu, A.-H., Mart\u00edn-Vide, C. (eds.) SLSP 2014. LNCS, vol. 8791, pp. 147\u2013158. Springer, Heidelberg (2014)"},{"key":"1_CR9","unstructured":"Dhondt, E., Verberne, S., Weber, N., Koster, C., Boves, L.: Using skipgrams and pos-based feature selection for patent classification. In: Computational Linguistics in the Netherlands (2012)"},{"issue":"1","key":"1_CR10","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s00521-012-1056-5","volume":"22","author":"Z Erenel","year":"2013","unstructured":"Erenel, Z., Alt\u0131n\u00e7ay, H.: Improving the precision-recall trade-off in undersampling-based binary text categorization using unanimity rule. Neural Comput. Appl. 22(1), 83\u2013100 (2013)","journal-title":"Neural Comput. Appl."},{"key":"1_CR11","first-page":"1289","volume":"3","author":"G Forman","year":"2003","unstructured":"Forman, G.: An extensive empirical study of feature selection metrics for text classification. J. Mach. Learn. Res. 3, 1289\u20131305 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR12","first-page":"1048","volume":"5","author":"E Gabrilovich","year":"2005","unstructured":"Gabrilovich, E., Markovitch, S.: Feature generation for text categorization using world knowledge. IJCAI 5, 1048\u20131053 (2005)","journal-title":"IJCAI"},{"issue":"4","key":"1_CR13","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/S1532-0464(03)00013-3","volume":"35","author":"R Grishman","year":"2003","unstructured":"Grishman, R., Huttunen, S., Yangarber, R.: Information extraction for enhanced access to disease outbreak reports. J. Biomed. Inform. 35(4), 236\u2013246 (2003)","journal-title":"J. Biomed. Inform."},{"issue":"3","key":"1_CR14","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1007\/s10618-012-0266-x","volume":"26","author":"F Gullo","year":"2013","unstructured":"Gullo, F., Domeniconi, C., Tagarelli, A.: Projective clustering ensembles. Data Min. Knowl. Disc. 26(3), 452\u2013511 (2013)","journal-title":"Data Min. Knowl. Disc."},{"issue":"1","key":"1_CR15","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. ACM SIGKDD Explor. Newsl. 11(1), 10\u201318 (2009)","journal-title":"ACM SIGKDD Explor. Newsl."},{"key":"1_CR16","unstructured":"Han, X., Sun, L.: An entity-topic model for entity linking. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 105\u2013115. Association for Computational Linguistics (2012)"},{"key":"1_CR17","unstructured":"Hatami, N., Chira, C., Armano, G.: A route confidence evaluation method for reliable hierarchical text categorization. arXiv preprint (2012). arXiv:1206.0335"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Huang, R., Riloff, E.: Classifying message board posts with an extracted lexicon of patient attributes. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1557\u20131562 (2013)","DOI":"10.18653\/v1\/D13-1162"},{"key":"1_CR19","series-title":"Theory and applications of natural language processing","first-page":"163","volume-title":"Multi-source, Multilingual Information Extraction and Summarization","author":"S Huttunen","year":"2012","unstructured":"Huttunen, S., Vihavainen, A., Du, M., Yangarber, R.: Predicting relevance of event extraction for the end user. In: Poibeau, T., Saggion, H., Piskorski, J., Yangarber, R. (eds.) Multi-source, Multilingual Information Extraction and Summarization. Theory and applications of natural language processing, pp. 163\u2013176. Springer, Berlin (2012)"},{"key":"1_CR20","unstructured":"Huttunen, S., Vihavainen, A., von Etter, P., Yangarber, R.: Relevance prediction in information extraction using discourse and lexical features. In: Proceedings of NoDaLiDa: the 18th Nordic Conference on Computational Linguistics. Riga, Latvia (2011)"},{"key":"1_CR21","unstructured":"Ji, H., Grishman, R., Dang, H.T., Griffitt, K., Ellis, J.: Overview of the tac 2010 knowledge base population track. In: Third Text Analysis Conference (TAC 2010) (2010)"},{"key":"1_CR22","unstructured":"Koller, D., Sahami, M.: Hierarchically classifying documents using very few words. Technical report 1997\u201375, Stanford InfoLab (February 1997)"},{"key":"1_CR23","first-page":"361","volume":"5","author":"DD Lewis","year":"2004","unstructured":"Lewis, D.D., Yang, Y., Rose, T.G., Li, F.: RCV1: a new benchmark collection for text categorization research. J. Mach. Learn. Res. 5, 361\u2013397 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR24","unstructured":"Liao, S., Grishman, R.: Using document level cross-event inference to improve event extraction. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 789\u2013797. Association for Computational Linguistics (2010)"},{"issue":"1","key":"1_CR25","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1016\/j.eswa.2007.10.042","volume":"36","author":"Y Liu","year":"2009","unstructured":"Liu, Y., Loh, H.T., Sun, A.: Imbalanced text classification: a term weighting approach. Expert Syst. Appl. 36(1), 690\u2013701 (2009)","journal-title":"Expert Syst. Appl."},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Mann, G.S., Yarowsky, D.: Multi-field information extraction and cross-document fusion. In: Proceedings of the 43rd annual meeting on association for computational linguistics, pp. 483\u2013490. Association for Computational Linguistics (2005)","DOI":"10.3115\/1219840.1219900"},{"key":"1_CR27","unstructured":"Moschitti, A., Ju, Q., Johansson, R.: Modeling topic dependencies in hierarchical text categorization. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, vol. 1, pp. 759\u2013767. Association for Computational Linguistics (2012)"},{"key":"1_CR28","first-page":"717","volume":"7","author":"S Patwardhan","year":"2007","unstructured":"Patwardhan, S., Riloff, E.: Effective information extraction with semantic affinity patterns and relevant regions. EMNLP-CoNLL 7, 717\u2013727 (2007)","journal-title":"EMNLP-CoNLL"},{"key":"1_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1007\/978-3-642-24016-4_10","volume-title":"Transactions on Computational Collective Intelligence V","author":"J Piskorski","year":"2011","unstructured":"Piskorski, J., Tanev, H., Atkinson, M., van der Goot, E., Zavarella, V.: Online news event extraction for global crisis surveillance. In: Nguyen, N.T. (ed.) Transactions on Computational Collective Intelligence V. LNCS, vol. 6910, pp. 182\u2013212. Springer, Heidelberg (2011)"},{"key":"1_CR30","unstructured":"Pokkunuri, S., Ramakrishnan, C., Riloff, E., Hovy, E., Burns, G.A.: The role of information extraction in the design of a document triage application for biocuration. In: Proceedings of BioNLP 2011 Workshop, pp. 46\u201355. Association for Computational Linguistics (2011)"},{"key":"1_CR31","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-540-24694-7_32","volume-title":"MICAI 2004: Advances in Artificial Intelligence","author":"RC Prati","year":"2004","unstructured":"Prati, R.C., Batista, G.E.A.P.A., Monard, M.C.: Class imbalances versus class overlapping: an analysis of a learning system behavior. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds.) MICAI 2004. LNCS (LNAI), vol. 2972, pp. 312\u2013321. Springer, Heidelberg (2004)"},{"key":"1_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1007\/978-3-642-32695-0_41","volume-title":"PRICAI 2012: Trends in Artificial Intelligence","author":"A Puurula","year":"2012","unstructured":"Puurula, A.: Scalable text classification with sparse generative modeling. In: Anthony, P., Ishizuka, M., Lukose, D. (eds.) PRICAI 2012. LNCS, vol. 7458, pp. 458\u2013469. Springer, Heidelberg (2012)"},{"key":"1_CR33","first-page":"93","volume-title":"Multi-source","author":"D Rao","year":"2013","unstructured":"Rao, D., McNamee, P., Dredze, M.: Entity linking: finding extracted entities in a knowledge base. In: Poibeau, T., Saggion, H., Piskorski, J., Yangarber, R. (eds.) Multi-source, pp. 93\u2013115. Multilingual Information Extraction and Summarization. Springer, Heidelberg (2013)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Roth, D., Yih, W.t.: Probabilistic reasoning for entity & relation recognition. In: Proceedings of the 19th international conference on Computational linguistics, vol.\u00a01, pp. 1\u20137. Association for Computational Linguistics (2002)","DOI":"10.3115\/1072228.1072379"},{"key":"1_CR35","unstructured":"Sil, A., Cronin, E., Nie, P., Yang, Y., Popescu, A.M., Yates, A.: Linking named entities to any database. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 116\u2013127. Association for Computational Linguistics (2012)"},{"key":"1_CR36","unstructured":"Sorower, M.S.: A literature survey on algorithms for multi-label learning. Technical report, Oregon State University, Corvallis, OR, USA, December 2010"},{"issue":"3","key":"1_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdwm.2007070101","volume":"3","author":"G Tsoumakas","year":"2007","unstructured":"Tsoumakas, G., Katakis, I.: Multi-label classification: an overview. Int. J. Data Warehouse. Min. (IJDWM) 3(3), 1\u201313 (2007)","journal-title":"Int. J. Data Warehouse. Min. (IJDWM)"},{"key":"1_CR38","first-page":"667","volume-title":"Data Mining and Knowledge Discovery Handbook","author":"G Tsoumakas","year":"2010","unstructured":"Tsoumakas, G., Katakis, I., Vlahavas, I.: Mining multi-label data. In: Maimon, O., Rokach, L. (eds.) Data Mining and Knowledge Discovery Handbook, pp. 667\u2013685. Springer, Heidelberg (2010)"},{"key":"1_CR39","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.knosys.2012.09.003","volume":"37","author":"S Wang","year":"2013","unstructured":"Wang, S., Li, D., Zhao, L., Zhang, J.: Sample cutting method for imbalanced text sentiment classification based on BRC. Knowl.-Based Syst. 37, 451\u2013461 (2013)","journal-title":"Knowl.-Based Syst."},{"issue":"1\u20132","key":"1_CR40","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1023\/A:1009982220290","volume":"1","author":"Y Yang","year":"1999","unstructured":"Yang, Y.: An evaluation of statistical approaches to text categorization. Inf. Retrieval 1(1\u20132), 69\u201390 (1999)","journal-title":"Inf. Retrieval"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Yangarber, R., Jokipii, L.: Redundancy-based correction of automatically extracted facts. In: Proceedings of HLT-EMNLP: Conference on Empirical Methods in Natural Language Processing, Vancouver, Canada, pp. 57\u201364 (2005)","DOI":"10.3115\/1220575.1220583"},{"key":"1_CR42","unstructured":"Yangarber, R., Steinberger, R.: Automatic epidemiological surveillance from on-line news in MedISys and PULS. In: Proceedings of IMED-2009: International Meeting on Emerging Diseases and Surveillance, Vienna, Austria (2009)"},{"issue":"3","key":"1_CR43","doi-asserted-by":"publisher","first-page":"2758","DOI":"10.1016\/j.eswa.2010.08.066","volume":"38","author":"W Zhang","year":"2011","unstructured":"Zhang, W., Yoshida, T., Tang, X.: A comparative study of TF*IDF, LSI and multi-words for text classification. Expert Syst. Appl. 38(3), 2758\u20132765 (2011)","journal-title":"Expert Syst. Appl."},{"key":"1_CR44","unstructured":"Zhuang, D., Zhang, B., Yang, Q., Yan, J., Chen, Z., Chen, Y.: Efficient text classification by weighted proximal SVM. In: Fifth IEEE International Conference on Data Mining (2005)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-19581-0_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T09:09:45Z","timestamp":1748423385000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-19581-0_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319195803","9783319195810"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-19581-0_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2015]]},"assertion":[{"value":"4 June 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}