Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network
Shanghai Jiao Tong University, Shanghai, China
arXiv:1510.06168 [cs.CL], (21 Oct 2015)
@article{wang2015partofspeech,
title={Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network},
author={Wang, Peilu and Qian, Yao and Soong, Frank K. and He, Lei and Zhao, Hai},
year={2015},
month={oct},
archivePrefix={"arXiv"},
primaryClass={cs.CL}
}
Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for tagging sequential data, e.g. speech utterances or handwritten documents. While word embedding has been demoed as a powerful representation for characterizing the statistical properties of natural language. In this study, we propose to use BLSTM-RNN with word embedding for part-of-speech (POS) tagging task. When tested on Penn Treebank WSJ test set, a state-of-the-art performance of 97.40 tagging accuracy is achieved. Without using morphological features, this approach can also achieve a good performance comparable with the Stanford POS tagger.
October 29, 2015 by hgpu
