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

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.

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

References in corpus (1)

• Natural Language Processing (almost) from Scratch

Cited by in corpus (15)

• Causality Extraction based on Self-Attentive BiLSTM-CRF with Transferred Embeddings
• Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Density
• Implicit Dimension Identification in User-Generated Text with LSTM Networks
• No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions)
• Fine-tuning ERNIE for chest abnormal imaging signs extraction
• Recurrent Neural Network based Part-of-Speech Tagger for Code-Mixed Social Media Text
• An Empirical Exploration of Skip Connections for Sequential Tagging
• Keystroke dynamics as signal for shallow syntactic parsing
• Character-based NMT with Transformer
• Simple Models for Word Formation in English Slang
• Sentiment Analysis of German Twitter
• Shortcut Sequence Tagging
• Building Context-aware Clause Representations for Situation Entity Type Classification
• Augmenting a BiLSTM tagger with a Morphological Lexicon and a Lexical Category Identification Step
• Transition-based Parsing with Context Enhancement and Future Reward Reranking