End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
复制标题

DOI：
10.18653/v1/p16-1101
复制
发表时间：
2016-03
期刊：
ArXiv
影响因子：
--
通讯作者：
Xuezhe Ma;E. Hovy
Xuezhe Ma;E. Hovy
中科院分区：
其他
文献类型：
--
作者：
Xuezhe Ma;E. Hovy

文献摘要

被引文献

相似文献

最先进的序列标记系统传统上需要大量的任务特定知识，以手工制作的特征和数据预处理的形式。本文采用双向LSTM、CNN和CRF相结合的方法，提出了一种自动从词级和字符级表示中获益的神经网络结构。我们的系统是真正的端到端，不需要特征工程或数据预处理，因此使其适用于广泛的序列标记任务。我们在两个数据集上评估了我们的系统，用于两个序列标记任务——Penn Treebank WSJ词性（POS）标记语料和CoNLL 2003命名实体识别（NER）语料。我们在这两个数据上都获得了最先进的性能——POS标记的准确率为97.55%，NER标记的准确率为91.21%。
State-of-the-art sequence labeling systems traditionally require large amounts of task-specific knowledge in the form of hand-crafted features and data pre-processing. In this paper, we introduce a novel neutral network architecture that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF. Our system is truly end-to-end, requiring no feature engineering or data pre-processing, thus making it applicable to a wide range of sequence labeling tasks. We evaluate our system on two data sets for two sequence labeling tasks --- Penn Treebank WSJ corpus for part-of-speech (POS) tagging and CoNLL 2003 corpus for named entity recognition (NER). We obtain state-of-the-art performance on both the two data --- 97.55\% accuracy for POS tagging and 91.21\% F1 for NER.