- I think direct quotation model is better for speech generation, but on the other hand, it is more convenient to have a language model, so let’s make one with RNNLM.
Morphological analysis with MaCab and [neologd
This page is auto-translated from /nishio/2018-09-27 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.