Table 4.

Performance comparison of ensemble models on the Yidu-S4K and self-annotated data sets.

Data set and model			Precision (%)		Recall (%)		F1-score (%)
Yidu-S4K
	BiLSTM-CRFa [64]	69.43		72.58		70.97
	ACNNb [69]	83.07		87.29		85.13
	ELMoc-lattice-LSTM-CRF [70]	84.69		85.35		85.02
	ELMo-BiLSTM-CRF [41]	—d		—		85.16
	ELMo-ETe-CRF [71]	82.08		86.12		85.59
	MSD_DT_NERf [72]	86.09		87.29		86.69
	Our model	90.37		88.22		89.28
Self-annotated
	BiLSTM-CRF	81.98		77.10		79.47
	Our model	84.24		84.99		84.61

^aBiLSTM-CRF: Bidirectional Long Short-Term Memory-conditional random fields.

^bACNN: all convolutional neural network.

^cELMo: Embeddings from Language Models.

^dNot available.

^eET: encoder from transformer.

^fMSD_DT_NER: multigranularity semantic dictionary and multimodal named entity recognition.