Use deep learning to create an eigenexpression recognizer that is independent of linguistic features and external knowledge. Eigenexpression recognizer made with deep learning - Ahogrammer

The model of Lample et al. - character based BiLSTMLSTM

  • Word-based BiLSTM
  • CRF I’m guessing unknown language is the reason they use a character-based model.

This page is auto-translated from /nishio/ディープラーニングで作る固有表現認識器 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.