search

zhiguowang / BiMPM

BiMPM: Bilateral Multi-Perspective Matching for Natural Language Sentences
Apache License 2.0
438 stars 150 forks source link

Testing on unlabelled data #15

Closed hadilnc01 closed 7 years ago

hadilnc01 commented 7 years ago

Now that I have the model trained and ready, how can I let it predict the labels of unlabelled questions?

In your instructions, you say that the test and trainings sets need to be in the following format:

label sentence#1 sentence#2 other_info

But if I want to run the model on unlabelled data, then I won't know the value of "label". How can I build my file and have the trained model predict the labels? I would have put dummy values for "label" but I'm worried it might affect the model's performance later on. Or is that not the case?

zhiguowang commented 7 years ago

Just put dummy values. I will not affect anything.

hadilnc01 commented 7 years ago

👍