A Note on Document Classification Methods with Small Training Data | Toshiyasu Matsushima Laboratory

Title	A Note on Document Classification Methods with Small Training Data (in Japanese)
Authors	Yasunari Maeda 、Hideki Yoshida 、Masakiyo Suzuki 、Toshiyasu Matsushima
Released Year	2011
Format	Journal
Category	Knowledge information processing
Jounal Name	IEEJ Transactions on Electronics, Information and Systems
Jounal Page	vol.131, no.8, pp.1459-1466
Published Year	2011
Published Month	8
Abstract （English）	Document classification is one of important topics in the field of NLP(Natural Language Processing). In the previous research a document classification method has been proposed which minimizes an error rate with reference to a Bayes criterion. But when the number of documents in training data is small, the accuracy of the previous method is low. So in this research we propose a new document classification method using estimating data in order to estimate prior distributions, which is based on the previous method. When the training data is small the accuracy of the proposed method is higher than the accuracy of the previous method. But when the training data is big the accuracy of the proposed method is lower than the accuracy of the previous method. So in this research we also propose another document classification method whose accuracy is higher than the accuracy of the previous method when the training data is small, and is almost the same as the accuracy of the previous method when the training data is big.
Note （English）	3
Manuscript
Presentation