search

clovaai / FocusSeq2Seq

[EMNLP 2019] Mixture Content Selection for Diverse Sequence Generation (Question Generation / Abstractive Summarization)
https://arxiv.org/abs/1909.01953
MIT License
113 stars 20 forks source link

Prediction #9

Open DivyaWadehra opened 4 years ago

DivyaWadehra commented 4 years ago

How to use question generation model to generate questions from the text we have?

chunduri11 commented 4 years ago

I was looking at the code to understand how "focus words" are derived. Looks like in the script "QG_data_loader.py" lines 265 to 295, they use source sentence and the target question to derive the "focus words".

My question is how is it possible to use this for prediction, where we will not have the target question to derive the "focus words" for a given sample.

Thanks. BTW thanks for making the code available, and it is very well written.