Skip to main content

Table 6 Final model results for entity extraction

From: Answering medical questions in Chinese using automatically mined knowledge and deep neural networks: an end-to-end solution

Model

Word vectorization

F1 Score

CRF

Pre-train

0.8132

Bi-LSTM

Pre-train

0.8341

Bi-LSTM+CRF

Pre-train

0.8563

Bi-LSTM

Co-train

0.8427

Bi-LSTM+CRF

(w/o context bridge)

Co-train

0.8590

Bi-LSTM+CRF

Co-train

0.8894

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us