Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network

Peilu Wang; Yao Qian; Frank K. Soong; Lei He; Hai Zhao

Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network

Computation and Language 2015-10-22 v1

Authors: Peilu Wang , Yao Qian , Frank K. Soong , Lei He , Hai Zhao

Abstract

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.

Keywords

part-of-speech tagging bidirectional long short-term memory recurrent neural network word embedding sequence labeling Penn Treebank Stanford POS tagger

Cite

@article{arxiv.1510.06168,
  title  = {Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network},
  author = {Peilu Wang and Yao Qian and Frank K. Soong and Lei He and Hai Zhao},
  journal= {arXiv preprint arXiv:1510.06168},
  year   = {2015}
}

Comments

rejected by ACL 2015 short, score: 4,3,2 (full is 5)

Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network

Abstract

Keywords

Cite

Comments

Related papers