search

harvardnlp / seq2seq-attn

Sequence-to-sequence model with LSTM encoder/decoders and attention
http://nlp.seas.harvard.edu/code
MIT License
1.26k stars 278 forks source link

single directory for dictionaries #8

Closed srush closed 7 years ago

srush commented 8 years ago

It seems potentially buggy to have to specify the source and target and character dictionary at decoding. Maybe we can just point to a directory with the dicts having fixed names? (this is what moses does)