An Incremental Learning Scheme for Perceptron Based Chinese Word Segmentation
Bin Han · Zhongwen xinxi xuebao · 2015
In this paper,we propose an incremental learning scheme for perceptron based Chinese word segmentation.Our method can perform continuous training over a fine tuned source domain model,enabling to deliver model without annotated data and re-training.Experimental results shows the scheme proposed can significantly improve adaptation performance on Chinese word segmentation and achieve comparable performance with traditional method.At the same time,our method can significantly reduce the model size and the training time.