Neural Conversational Model in TorchAt 2019-03-14 fate wrote in BLOG. 2533 viewer.
Neural Conversational Model in Torch
Forked from https://github.com/chenb67/neuralconvo
Use https://github.com/dgkae/dgk_lost_conv as training corpus. The chinese sentenses should be splited by semantic words, using '/'. We modify cornell_movie_dialog.lua to support it. Lua save all string(e.g. chinese) all in multibyte, so in chinese the formal pl.lexer is not working. We use outsider word-splitting tool and using '/' as the tag.