shrimai

You would have to train your own model on the wow dataset using the DOHA train script provided in the code.

Yes I concatenate all the sentences of all the retrieved passages (approx 7 passages for each sample) as d_i of each sample. I don't make any use of label. @Reveyer...

All the content pertaining to this project is being hosted on CMU servers and unfortunately I am not longer at CMU. I will try to contact the admin of the...

The ground truth index positions should only be used for evaluating the model performance (on dev and test sets for which you have ground truth). If you don't know the...

This is correct. For B-TSort and L-TSort techniques we split sentences of a document in different pairs and get constraints from the pairs. I suppose you are not facing high...