LSTM-CRF Models for Named Entity Recognition

Changki LEE  

IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.4   pp.882-887
Publication Date: 2017/04/01
Online ISSN: 1745-1361
Type of Manuscript: PAPER
Category: Natural Language Processing
LSTM-CRF,  LSTM RNN,  recurrent neural network,  name entity recognition,  

Full Text: PDF(1.3MB)
>>Buy this Article

Recurrent neural networks (RNNs) are a powerful model for sequential data. RNNs that use long short-term memory (LSTM) cells have proven effective in handwriting recognition, language modeling, speech recognition, and language comprehension tasks. In this study, we propose LSTM conditional random fields (LSTM-CRF); it is an LSTM-based RNN model that uses output-label dependencies with transition features and a CRF-like sequence-level objective function. We also propose variations to the LSTM-CRF model using a gate recurrent unit (GRU) and structurally constrained recurrent network (SCRN). Empirical results reveal that our proposed models attain state-of-the-art performance for named entity recognition.