You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for your great work. In the Infoseek paper, the quality of queries is estimated with human annotation, providing evidence section of the query within the document. I wonder if you could include the evidence section information into the dataset or provide the files, which would greatly facilitate further research using this dataset!
The text was updated successfully, but these errors were encountered:
Thanks for your interest! Unfortunately, I don't have the access to the data.
But I recall a simple string matching of the answer vs wikipedia article should have around 6-75% coverage.
Thank you for your great work. In the Infoseek paper, the quality of queries is estimated with human annotation, providing evidence section of the query within the document. I wonder if you could include the evidence section information into the dataset or provide the files, which would greatly facilitate further research using this dataset!
The text was updated successfully, but these errors were encountered: