Issue when using Guided Alignment

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

Issue when using Guided Alignment #106

Open Anupama94 opened 6 years ago

Anupama94 commented 6 years ago

Hi, When training the model with guided alignment, I get the following error. ./s2sa/data.lua:174: bad argument #2 to 'sub' (out of range at /home/anupama/torch/pkg/torch/generic/Tensor.c:304) I have prepared the alignment file as suggested in the documentation. Any suggestions to overcome this error? Thank you.