[Corpora-List] Fwd: Statistical Significance Tool like compare.pl

[Miguel Ballesteros]

Hi,

this is the link I have. It is not cached in google anymore. There may be a
problem with their server.
You may try to contact the authors:
http://www.lrec-conf.org/proceedings/lrec2008/pdf/52_paper.pdf

Miguel



On 2 May 2013 10:47, Riyaz <riyaz.ah.bhat at gmail.com> wrote:

> Hi Miguel,
>
>
> Your link doesn't work. Could you please check it.
>
>
> On Thu, May 2, 2013 at 2:02 PM, Miguel Ballesteros <
> miguelballesteros1 at gmail.com> wrote:
>
>> Hi Ryaz,
>> you can try MaltEval. that can also produce statistical significance
>> tests (McNemar's) when you provide more than one output file
>>
>> http://w3.msi.vxu.se/~jni/malteval/
>>
>> Best,
>> Miguel
>>
>>
>> On 2 May 2013 10:19, Djamé Seddah <djame.seddah at free.fr> wrote:
>>
>>> Hi,
>>> I've put the version I have momentary online
>>>
>>> http://pauillac.inria.fr/~seddah/compare.pl
>>>
>>>
>>> Djamé
>>>
>>>
>>> Le 2 mai 2013 à 09:58, Riyaz a écrit :
>>>
>>> > Hi,
>>> >
>>> > Can anyone direct me to some tool available online that can compute
>>> > statistical significance for parsing results.
>>> > I tried searching for Randomized Parsing Evaluation Comparator
>>> (Statistical
>>> > Significance Tester for evalb Output) By Dan Bikel, but the available
>>> link
>>> > doesn't work anymore.
>>> >
>>> > --
>>> > Thanks
>>> > Riyaz Ahmad
>>> > _______________________________________________
>>> > UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
>>> > Corpora mailing list
>>> > Corpora at uib.no
>>> > http://mailman.uib.no/listinfo/corpora
>>>
>>>
>>> _______________________________________________
>>> UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
>>> Corpora mailing list
>>> Corpora at uib.no
>>> http://mailman.uib.no/listinfo/corpora
>>>
>>
>>
>>
>> --
>> Miguel Ballesteros
>>
>>
>>
>
>
> --
> Regards
> Riyaz Ahmad
>



-- 
Miguel Ballesteros
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20130502/39796193/attachment.htm>
-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora