This idea has been merged into another idea. To comment or vote on this idea, please visit WDS-I-185 Relevancy Training for Passages.
Currently, I can train Watson on document level. Can that be extended to passage level? Sometimes, the first passage that is getting extracted is not the relevant passage. It would be great if I could train Watson on passage level as well.
Why is it useful?
|Who would benefit from this IDEA?||Developers that are using Watson Assistant to retrieve passage from Watson Discovery service|
How should it work?