no code implementations • RANLP 2021 • An Nguyen Le, Hajime Morita, Tomoya Iwakura
Biomedical Named Entities are complex, so approximate matching has been used to improve entity coverage.
no code implementations • IJCNLP 2017 • An Nguyen Le, Ander Martinez, Akifumi Yoshimoto, Yuji Matsumoto
In order to assess the performance, we construct model based on an attention mechanism encoder-decoder model in which the source language is input to the encoder as a sequence and the decoder generates the target language as a linearized dependency tree structure.