Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network
This improves POS tagging accuracy for natural language processing applications, but is incremental as it combines existing methods.
The paper tackled part-of-speech tagging by using a bidirectional LSTM recurrent neural network with word embeddings, achieving a state-of-the-art accuracy of 97.40% on the Penn Treebank WSJ test set.
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.