Comment by 0xlogk
8 days ago
The paper mentions they used Wikipedia as search corpus. The repo states they plan to expand to Google, Bing APIs. I wonder how they will handle evolving search corpora, ie. if continual RL updates will be needed.
8 days ago
The paper mentions they used Wikipedia as search corpus. The repo states they plan to expand to Google, Bing APIs. I wonder how they will handle evolving search corpora, ie. if continual RL updates will be needed.
No comments yet
Contribute on Hacker News ↗