Re: Corpora: Statistical significance of tagging differences

Khalid CHOUKRI (choukri@elda.fr)
Wed, 17 Mar 1999 15:18:13 +0100

--=====================_4294735==_.ALT
Content-Type: text/plain; charset="us-ascii"

I suggest to contact Patrick Paroubeck who did a similar work in the framework
of a collaborative project (called GRACE) funded by the French gouvernment
and other French-speaking countries gouvernements
His email: Patrick PAROUBEK <pap@limsi.fr>

Khalid Choukri
ELRA CEO
At Wednesday 3/17/99 11:24 AM(+0000), Mark Stevenson wrote:
>Hi,
>
>I've been experimenting with PoS taggers operating under different conditions
so
>that I have several different taggings of the same corpus. I also have a
"gold
>standard" annotation for that text, so I can work out the percentage correct
>for each tagging.
>
>I was wondering if anyone knows of the appropriate statistical tests which
could
>be applied to determine whether the differences in tagging performace are
>statistically significant?
>
>Any pointers would be appreciated.
>
>Thanks in advance,
>Mark Stevenson
>
>---------------------------------------------------------------------------

---
>Mark Stevenson                   
>Research Assistant                    marks@dcs.shef.ac.uk
>Natural Language Processing Group     http://www.dcs.shef.ac.uk/~marks   
>Sheffield University                  (0114) 222 1899  
>-----------------------------------------------------------------------------
> 
*************************************************************
Khalid CHOUKRI 
ELRA CEO
mailto:choukri@elda.fr
Web: http://www.icp.grenet.fr/ELRA/home.html
Tel. +33 1 43 13 33 33 - Fax. +33 1 43 13 33 30
Mail: 55 Rue Brillat-Savarin, 75013 Paris France
***************************************************************


--=====================_4294735==_.ALT
Content-Type: text/html; charset="us-ascii"



I suggest to contact Patrick Paroubeck who did a similar work in the
framework of a collaborative project (called GRACE)  funded by the
French  gouvernment and other French-speaking countries
gouvernements 

His email: Patrick PAROUBEK <pap@limsi.fr>



Khalid Choukri

ELRA CEO

At Wednesday 3/17/99 11:24 AM(+0000), Mark Stevenson wrote:

>Hi,

>

>I've been experimenting with PoS taggers operating under different
conditions so

>that I have several different taggings of the same corpus. I also
have a "gold

>standard" annotation for that text, so I can work out the
percentage correct

>for each tagging. 

>

>I was wondering if anyone knows of the appropriate statistical tests
which could

>be applied to determine whether the differences in tagging performace
are 

>statistically significant? 

>

>Any pointers would be appreciated.

>

>Thanks in advance,

>Mark Stevenson

>

>------------------------------------------------------------------------------

>Mark
Stevenson                  


>Research
Assistant                   
marks@dcs.shef.ac.uk

>Natural Language Processing Group    
http://www.dcs.shef.ac.uk/~marks  


>Sheffield
University                 
(0114) 222 1899  

>-----------------------------------------------------------------------------

> 


*************************************************************


Khalid CHOUKRI 


ELRA CEO


mailto:choukri@elda.fr


Web:
http://www.icp.grenet.fr/ELRA/home.html


Tel. +33 1 43 13 33 33 - Fax. +33 1 43 13 33 30


Mail: 55 Rue Brillat-Savarin, 75013 Paris France


***************************************************************




--=====================_4294735==_.ALT--