lucene-java-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Robert Muir <>
Subject Re: Precision-recall curve with /contrib/benchmark/quality
Date Wed, 26 May 2010 12:39:41 GMT
Personally I use the generated submission.txt, and run it thru
trec_eval to get all numbers.

by default, trec_eval will dump ircl_prn.xxxx values, and you could
plug them in openoffice.
I prefer to use trec_eval as the results from the benchmark summary
often differ with trec_eval.

it would be great if somehow this process could be improved by default.

Nicola Ferro mentioned on the list once that for the CLEF work, they
have written a JNI wrapper around trec_eval to access all its
computations, this might be one thing we could consider, then we could
access the correct calculations and produce fancy output.

On Wed, May 26, 2010 at 5:32 AM, calin014 <> wrote:
> Hi,
> I am testing some ranking methods with /contrib/benchmark/quality package,
> and i was wondering if there is a simple way of building a precision-recall
> graph with the info gathered(maybe QualityStats.RecallPoint).
> Thanks
> --
> View this message in context:
> Sent from the Lucene - Java Users mailing list archive at
> ---------------------------------------------------------------------
> To unsubscribe, e-mail:
> For additional commands, e-mail:

Robert Muir

To unsubscribe, e-mail:
For additional commands, e-mail:

View raw message