search

allenai / deep_qa

A deep NLP library, based on Keras / tf, focused on question answering (but useful for other NLP too)
Apache License 2.0
404 stars 132 forks source link

Testing the model and getting answer to a new question #413

Closed marilenaoita closed 6 years ago

marilenaoita commented 6 years ago

Hi, I have trained the bidaf model on squad, and I have the following questions

  1. predictions = score_dataset("[..]reading_comprehension/bidaf_squad.json") gives: Traceback (most recent call last): File "", line 1, in TypeError: score_dataset() missing 1 required positional argument: 'dataset_files' Another argument is required, and I try to add the path to the .tsvs, but it doesnt work.

  2. There is no information (at least explicit) in the documentation on how to get the answer to a new question. Could you give an example/specify the function to do this? thanks !

DeNeutoy commented 6 years ago

Hi there - DeepQA is not supported anymore. It has been superseded by AllenNLP, so unfortunately we aren't going to be able to help you. Please try using AllenNLP - you should find it considerably easier to use.

marilenaoita commented 6 years ago

Thanks for your answer. I'll follow the advice. Best regards, Marilena

On Sun, Apr 22, 2018 at 9:16 PM, Mark Neumann notifications@github.com wrote:

Hi there - DeepQA is not supported anymore. It has been superseded by AllenNLP https://github.com/allenai/allennlp, so unfortunately we aren't going to be able to help you. Please try using AllenNLP - you should find it considerably easier to use.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/allenai/deep_qa/issues/413#issuecomment-383405339, or mute the thread https://github.com/notifications/unsubscribe-auth/AG2sXr1c_0Bf0sNn7HvEirzUcsnuXBq9ks5trNbygaJpZM4Te2UX .