A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding

Abstract

Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for modeling and predicting sequential data, e.g. speech utterances or handwritten documents. In this study, we propose to use BLSTM-RNN for a unified tagging solution that can be applied to various tagging tasks including part-of-speech tagging, chunking and named entity recognition. Instead of exploiting specific features carefully optimized for each task, our solution only uses one set of task-independent features and internal representations learnt from unlabeled text for all tasks.Requiring no task specific knowledge or sophisticated feature engineering, our approach gets nearly state-of-the-art performance in all these three tagging tasks.

Rejected by EMNLP 2015, score: 4,3,3 (full is 5)

References in corpus (1)

• Natural Language Processing (almost) from Scratch

Cited by in corpus (8)

• Semantic Tagging with Deep Residual Networks
• Implicit Dimension Identification in User-Generated Text with LSTM Networks
• Memorized Sparse Backpropagation
• A Minimal Span-Based Neural Constituency Parser
• Byte-based Language Identification with Deep Convolutional Networks
• Going Wider: Recurrent Neural Network With Parallel Cells
• Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages
• Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation