A simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly
GNU General Public License v3.0
570
stars
270
forks
source link
In an open chatbot domain, twitter, should we have 2 vocabs? #42
Open
LeenaShekhar opened 7 years ago
In cases where there is no explicit need for 2 vocabs (unlike NMT), should we have 2 separate vocabularies or just use one?