ИСТИНА

We describe two hybrid neural network models for named entity recognition (NER) in texts, as well as results of experiments with them. The first model, namely BiLSTM-CRF, is known and used for NER, while the other model named Gated-CNN-CRF is proposed in this work. It combines convolutional neural networks (CNN), gated linear units, and conditional random fields (CRF). Both models were trained and tested for NER on the Chinese tagged corpus and also on datasets for English and Russian. All resulted scores of precision, recall and F1-measure for both models are close to the state-of-the-art for NER, and for the English dataset CoNLL-2003, Gated-CNN-CRF model achieves 92.66 of F1-measure, outperforming the known result.