Document Classification by CNN+LSTM using Kanji radicals as features | Artificial Intelligence R&D Engineers Group - Nextremer Inc. polarisation] by CNN+LSTM using radical (of a kanji character) as a feature
Use Kanji Structure Information Database to obtain radical information
- It would be good to combine with Kanji Dividend Chart by Grade.
This page is auto-translated from /nishio/部首+CNN+LSTMで極性判定 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.