vigyasharma commented on PR #13525: URL: https://github.com/apache/lucene/pull/13525#issuecomment-2237194980
> The pattern doesn't work well with ColBERT esque models. +1.. Good question, @navneet1v. I had the same doubts before starting this effort. There is some discussion in [12313](https://github.com/apache/lucene/issues/12313#issuecomment-2044076948). Basically, Multi-vectors allow for ColBERT style late interaction models, where queries and documents can both be represented by multiple vector values, and you do a similarity measure using all those values (e.g. sum(max(similarity))). They gather contextual interaction across different parts of a query and a document, without incurring the query-time computational overheads of cross-encoder models. Nested block joins on the other hand compute distance with a single vector value and then aggregate. That doesn't work well here, esp. with both query and doc multi-vectors. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@lucene.apache.org For additional commands, e-mail: issues-h...@lucene.apache.org
