Skip to main content

Table 15 Comparison of question answering (QA) models

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

Model

F1

F1-STD

P@1

P@1-STD

Bi-LSTM

0.521

0.037

0.556

0.056

Attention+Bi-LSTM

0.546

0.023

0.572

0.025

Only MemNN

0.583

0.031

0.604

0.028

Our model

0.639

0.024

0.661

0.023

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us