For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
LSTM-CRF Models for Named Entity Recognition
IEICE TRANSACTIONS on Information and Systems
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.