Allow fixed/initialized word embeddings

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

Closed srush closed 8 years ago

srush commented 8 years ago

Would be nice to allow people to start/stay with their own word embeddings for small domain problems.