LiberAI/NSpM

Attention for LSTM

D0nPiano opened this issue · 2 comments

D0nPiano commented

Hello,
I really like your work on using seq2seq for creating SPARQL queries - just one question: Was there a specific reason not to include attention while training? As far as I understood the tensorflow NMT guilde, you would have to add something like --attention=scaled_luong to the options in your train.sh. Did you evaluate whether it works better with/without attention?
Greetings!

mommi84 commented

Hi @D0nPiano and thanks for your interest!

As ours is a work in progress, we haven't activated yet the attention mechanism, but we definitely plan to evaluate that. Thanks for pointing this out, though.

Cheers!

  • 👍1
mommi84 commented

Solved in PR #50.