Learning to Classify Texts Using Positive and Unlabeled Data

Keywords

Computer science, Classifier (UML), Artificial intelligence, Support vector machine, Class (philosophy)

References

• Exploiting Relations Among Concepts to Acquire Weakly Labeled Training DataJoseph Bockhorst, Mark Craven — 2002
• Active + Semi-supervised Learning = Robust Multi-View LearningIon Muslea, Steven Minton, Craig A. Knoblock — 2002
• Making large scale SVM learning practicalThorsten Joachims — 1998
• Advances in kernel methods: support vector learningBernhard Schölkopf, Christopher J. C. Burges, Alexander J. Smola — 1999
• Enhancing Supervised Learning with Unlabeled DataSally A. Goldman, Yan Zhou — 2000
• Partially Supervised Classification of Text DocumentsBing Liu, Wee Sun Lee, Philip S. Yu — 2002
• Introduction to Modern Information RetrievalGerard Salton, Michael J. McGill — 1983
• Efficient noise-tolerant learning from statistical queriesMichael Kearns — 1998
• A re-examination of text categorization methodsYiming Yang, Xin Liu — 1999
• PEBL: positive example based learning for Web page classification using SVMHwanjo Yu, Jiawei Han, Kevin Chen–Chuan Chang — 2002
• Combining labeled and unlabeled data with co-trainingAvrim Blum, Tom M. Mitchell — 1998
• Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paperA. P. Dempster, N. M. Laird, Donald B. Rubin — 1977
• A sequential algorithm for training text classifiersDavid Lewis, William A. Gale — 1994
• Text Classification from Labeled and Unlabeled Documents using EMKamal Nigam, Andrew Kachites McCallum, Sebastian Thrun — 2000
• Semi-supervised Clustering by SeedingSugato Basu, Arindam Banerjee, Raymond J. Mooney — 2002
• Learning from positive and unlabeled examplesFrançois Denis, Rémi Gilleron, Fabien Letouzey — 2000
• Estimating the Support of a High-Dimensional DistributionBernhard Schölkopf, John Platt, John Shawe‐Taylor — 2001
• The Nature of Statistical Learning TheoryVladimir Vapnik — 2000
• The effect of adding relevance information in a relevance feedback environmentChris Buckley, Gerard Salton, James Allan — 1994
• The Nature of Statistical Learning TheoryVladimir Vapnik — 1995

Cited by

• Learning to Identify Unexpected Instances in the Test SetXiaoli Li, Bing Liu, See‐Kiong Ng — 2007
• Positive Unlabeled Learning for Data Stream ClassificationXiaoli Li, Philip S. Yu, Bing Liu — 2009
• Personalised ontology learning and mining for web information gatheringXiaohui Tao — 2009
• TPN 2 : Using positive-only learning to deal with the heterogeneity of labeled and unlabeled dataNikolaos Trogkanis, Γεώργιος Παλιούρας — 2006
• Robust content-based image retrieval of multi-example queriesJun Zhang — 2011
• Relevance feature discovery for text analysisAbdulmohsen Algarni — 2011
• Identification of Consumer Adverse Drug Reaction Messages on Social MediaMing Yang, Xiaodi Wang, Melody Y. Kiang — 2013
• Partially Supervised Text Classification with Multi-Level ExamplesTao Liu, Xiaoyong Du, Yongdong Xu — 2011
• Automatic Generation of Background Text to Aid ClassificationSarah Zelikovitz, Robert Häfner — 2004
• Semi-Supervised Text Classification Using Positive and Unlabeled DataShuang Yu, Xueyuan Zhou, Chunping Li — 2006
• Learning from positive and unlabeled examples in biology. (Méthodes d'apprentissage statistique à partir d'exemples positifs et indéterminés en biologie)Fantine Mordelet — 2010
• Improving Text Classification Using EM with Background TextSarah Zelikovitz, Haym Hirsh — 2005
• Positive Unlabeled Learning Algorithm for One Class Classification of Social Text Stream with only very few Positive Training SamplesAbhinandan Vishwakarma — 2015
• POLYGLOT-NER: Massive Multilingual Named Entity RecognitionRami Al‐Rfou, Vivek Kulkarni, Bryan Perozzi — 2014
• Analysis of Mass Spectrometry Data for Protein Identification In Complex Biological MixturesM. A. Spivak — 2010
• Analyse des propriétés stationnaires et des propriétés émergentes dans les flux d'informations changeant au cours du temps. (Analysis of stationary and emerging properties in information flows changing over time)Randa Kassab — 2009
• A Novel Reliable Negative Method Based on Clustering for Learning from Positive and Unlabeled ExamplesBangzuo Zhang, Wanli Zuo — 2008
• Query-By-Multiple-Examples using Support Vector MachinesDell Zhang, Wee Sun Lee — 2009
• Knowledge discovery using pattern taxonomy model in text miningSheng‐Tang Wu — 2007
• Classifying biomedical citations without labeled training examplesXiaoli Li, Raj Joshi, S. Ramachandaran — 2004

Related papers

• PEBL: Web page classification without negative examplesHwanjo Yu, Jiawei Han, Kai-Wei Chang — 2004
• Building text classifiers using positive and unlabeled examplesB. Liu, Y. Dai, Xiaoli Li — 2003
• Learning with Positive and Unlabeled Examples Using Weighted Logistic RegressionWee Sun Lee, Bing Liu — 2003
• Estimating the Support of a High-Dimensional DistributionBernhard Schölkopf, John Platt, John Shawe‐Taylor — 2001
• Analysis of Learning from Positive and Unlabeled DataMarthinus Christoffel du Plessis, Gang Niu, Masashi Sugiyama — 2014
• Learning from positive and unlabeled examplesFrançois Denis, Rémi Gilleron, Fabien Letouzey — 2000
• Learning classifiers from only positive and unlabeled dataCharles Elkan, Keith Noto — 2008
• Machine learning in automated text categorizationFabrizio Sebastiani — 2001
• PEBL: positive example based learning for Web page classification using SVMHwanjo Yu, Jiawei Han, Kevin Chen–Chuan Chang — 2002
• Partially Supervised Classification of Text DocumentsBing Liu, Wee Sun Lee, Philip S. Yu — 2002