基于序列标注的中文分词、词性标注模型比较分析

A Comparison Study of Sequence Labeling Methods for Chinese Word Segmentation,POS Tagging Models

该文对三种不同的分词词性标注模型进行了比较。这三种模型分别为一个序列标注串行模型,一个基于字分类的联合模型和一个将这两种模型使用Stacked Learning框架进行集成的融合模型。通过在《人民日报》、CoNLL09、CTB5.0和CTB7.0四个数据集上进行比较分析,最终实验结果表明分类联合模型能取得比较好的速度,融合模型能取得比较好的准确率,而普通串行模型处于速度和准确率的平衡位置。最后该文将准确率最好的融合模型和相关前沿工作在CTB5.0和CTB7.0上进行了对比,该融合模型均取得了最好的结果。

In this paper, we compare three different Chinese word segmentation and POS tagging models. Accuracy and speed are considered during the comparison. First of these three models are pipelinesequential model. The sec- ond is a joint model for word segmentation and POS tagging, andthe last one is a combination of two modelsmen- tionedabove with a stacked learning framework. We conduct experiments on four data sets, including People Daily, CoNLL09, CTB5.0 and CTB7.0. Experimental results show that the joint model achieves the fastest speed while the stacked learning model achievesthe highest accuracy. Finally, we compare our stacked learning model with state of-the-art systems on data sets CTB5.0 and CTB7.0 and our model achieve the best performance in this comparison.