HIGHLIGHTS
SUMMARY
To expert knowledge, self-learning or data-driven approaches have been used in machine_learning for information extraction from text. Deep learning (DL) is another subdomain of machine_learning (ML) that uses neural_networks for extracting information. The authors have compared a hybrid method using expert input and compared it with machine_learning methods. The authors used two different deep learning architectures based on bidirectional long short-term memory neural_networks (Bi-LSTM): one with 5 layers (Bi-LSTM_simple) (Appendix 3) adapted from the Keras library and another with 13 layers including dropout layers (Bi-LSTM_dropout) (Appendix 4). The . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.