[
https://issues.apache.org/jira/browse/SOLR-8183?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14968016#comment-14968016
]
Ajinkya Kale commented on SOLR-8183:
------------------------------------
Here is a hacky piece I wrote in a few hours
https://github.com/ajkl/solr-ltr-plugin
Its not polished but it works.
I would also like to mention that I could write such a functionality without
knowing Solr internals and codebase is a big win for Solr and its plugin
architecture! Thank you all who made it possible.
> Add Learning to Rank framework to Solr
> --------------------------------------
>
> Key: SOLR-8183
> URL: https://issues.apache.org/jira/browse/SOLR-8183
> Project: Solr
> Issue Type: New Feature
> Reporter: Ajinkya Kale
>
> Add a Learning to Rank or Machine Learned Ranking framework to Solr. The
> framework should be able to
> 1. Generate user-result-click tracking logs
> 2. Learning/Training component which is based on something like Ranklib
> (http://sourceforge.net/p/lemur/wiki/RankLib/)
> 3. Push the model learnt in step 2 to Solr through the existing rerank
> framework
> I have a very crude experimental code for step 2 and 3 working (thanks to the
> help from Joel Bernstein).
> For step 1 I was wondering if Solr has an open source version of
> https://docs.lucidworks.com/display/lweug/Click+Scoring+Relevance+Framework
> If there existing something like this then it wont be hard to close the loop
> and have an nice feedback loop implementation on LTR framework.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
