how to provide samples in answerability and waht is the output for that about multi-task-nlp HOT 2 OPEN

On Wed, Aug 12, 2020 at 1:05 PM Saransh Mehta ***@***.***> wrote: Hi @mayankpathaklumiq <https://github.com/mayankpathaklumiq> Thanks for writing. The concept of answerability is that given a query and a paragraph (context passage), determine where that query can be answered from given passage or not. Hence, the input is query, passage and label. Label is 0 (not-answerable) and 1 (for answerable). Similarly, the output produced will either be 0 or 1 while inferring on trained model. This is mentioned in the answerability example as well, which transforms the MSMARCO data for this task. After running the transformations part in above example, you can go to the data directory and checkout the created data files - msmarco_answerability_dev.tsv (or train/test) to know how is the final input data. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#7 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/APYLFHJ2NXLTLOGBQO7I3MTSAJA43ANCNFSM4P25B2HA> .