The nature of statistical learning theory
The nature of statistical learning theory
A maximum entropy approach to natural language processing
Computational Linguistics
Combining labeled and unlabeled data with co-training
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
Knowledge lean word-sense disambiguation
AAAI '98/IAAI '98 Proceedings of the fifteenth national/tenth conference on Artificial intelligence/Innovative applications of artificial intelligence
A Winnow-Based Approach to Context-Sensitive Spelling Correction
Machine Learning - Special issue on natural language learning
Text Classification from Labeled and Unlabeled Documents using EM
Machine Learning - Special issue on information retrieval
BoosTexter: A Boosting-based Systemfor Text Categorization
Machine Learning - Special issue on information retrieval
Analyzing the effectiveness and applicability of co-training
Proceedings of the ninth international conference on Information and knowledge management
Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Automatic Rule Acquisition for Spelling Correction
ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning
Transductive Inference for Text Classification using Support Vector Machines
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Maximum entropy models for natural language ambiguity resolution
Maximum entropy models for natural language ambiguity resolution
A simple approach to building ensembles of Naive Bayesian classifiers for word sense disambiguation
NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
Unsupervised word sense disambiguation rivaling supervised methods
ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
ACL '94 Proceedings of the 32nd annual meeting on Association for Computational Linguistics
Scaling to very very large corpora for natural language disambiguation
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Two supervised learning approaches for name disambiguation in author citations
Proceedings of the 4th ACM/IEEE-CS joint conference on Digital libraries
Using weak supervision in learning Gaussian mixture models
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
A cross-corpus study of unsupervised subjectivity identification based on calibrated EM
WASSA '11 Proceedings of the 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis
Naïve bayes classifier based watermark detection in wavelet transform
MRCS'06 Proceedings of the 2006 international conference on Multimedia Content Representation, Classification and Security
Data & Knowledge Engineering
Chinese terminology extraction using EM-Based transfer learning method
CICLing'13 Proceedings of the 14th international conference on Computational Linguistics and Intelligent Text Processing - Volume Part I
What's the deal?: identifying online bargains
AWC '13 Proceedings of the First Australasian Web Conference - Volume 144
Hi-index | 0.00 |
Combining a naive Bayes classifier with the EM algorithm is one of the promising approaches for making use of unlabeled data for disambiguation tasks when using local context features including word sense disambiguation and spelling correction. However, the use of unlabeled data via the basic EM algorithm often causes disastrous performance degradation instead of improving classification performance, resulting in poor classification performance on average. In this study, we introduce a class distribution constraint into the iteration process of the EM algorithm. This constraint keeps the class distribution of unlabeled data consistent with the class distribution estimated from labeled data, preventing the EM algorithm from converging into an undesirable state. Experimental results from using 26 confusion sets and a large amount of unlabeled data show that our proposed method for using unlabeled data considerably improves classification performance when the amount of labeled data is small.