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.
Cite
@article{arxiv.1511.00215,
title = {A Unified Tagging Solution: Bidirectional LSTM Recurrent Neural Network with Word Embedding},
author = {Peilu Wang and Yao Qian and Frank K. Soong and Lei He and Hai Zhao},
journal= {arXiv preprint arXiv:1511.00215},
year = {2015}
}
Comments
Rejected by EMNLP 2015, score: 4,3,3 (full is 5)