-
Notifications
You must be signed in to change notification settings - Fork 2.1k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Add RCIReader for TableQA #1909
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM! Left one tiny comment regarding docs. Feel free to merge after this has been addressed
Each row and each column is given a score with regard to the query by two separate models. The score of each cell | ||
is then calculated as the sum of the corresponding row score and column score. Accordingly, the predicted answer is | ||
the cell with the highest score. | ||
""" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we add one line that explains the core pros/cons to TableReader? (e.g. confidence scores, aggregation options ...)
This PR adds the possibility to use Row-Column-Intersection models as described in this paper and its associated repository.
Open To-Dos: