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

TL;DR

This paper demonstrates that a bidirectional LSTM RNN combined with word embeddings achieves state-of-the-art accuracy in part-of-speech tagging, comparable to traditional methods without morphological features.

Contribution

It introduces the use of BLSTM-RNN with word embeddings for POS tagging, achieving high accuracy without relying on morphological features.

Findings

Achieved 97.40% accuracy on Penn Treebank WSJ test set.

Comparable performance to Stanford POS tagger without morphological features.

Validated effectiveness of BLSTM-RNN with word embeddings for sequence tagging.

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.