<html>
Hi John and Edina,<br>
<br>
I am currently developing a morpho-semantics parser for French (DériF)
based on linguistic constraints. Words decomposition is recursive,
hierarchical and any complex input (be it a neologism or an attested
word) is provided a pseudo-definition wrt to the morphological process
which relates it to its base.<br>
<br>
Derif is developing one morphological process type (= module : for
instance noun-to-adjective -ique suffixation is a module) after the
other, so that it does not account for all morphological processes yet;
so far,<br>
it is able to parse around 30 word formation types, including
suffixation, prefixation rules, conversion and neoclassical
compounding.<br>
<br>
It is a simple Perl program, that requires only to have Perl 5.8
installed.<br>
<br>
DeriF recent developments focus on biomedical terminology. Last DériF
version allows neoclassical compounds to be grouped into lexical classes,
by calculating synonymy, hyponymy and approximation
relations.<br>
<br>
Here is an example:<br>
===========================================<br>
gastralgie/NOM==><br>
<x-tab> </x-tab>[ [ gastr
N* ] [ algie N* ] NOM ]
<x-tab> </x-tab><br>
(gastralgie/NOM,
algie/N*)<x-tab> </x-tab><br>
" douleur (du -- liée au) estomac "<br>
<br>
Constituants = /gastr/algie/<br>
<br>
gastralgie/NOM: synonym of gastrodynie/NOM,
<x-tab> </x-tab>stomacalgie/NOM, stomacodynie/NOM,
<x-tab> </x-tab>stomachodynie/NOM,
(gastralgique/ADJ)<br>
gastralgie/NOM: subtype of abdominalgie/NOM<br>
gastralgie/NOM: see also entéralgie/NOM, <br>
<x-tab> </x-tab>entérodynie/NOM,
gastrite/NOM, <br>
<x-tab> </x-tab>hépatalgie/NOM,
hépatodynie/NOM, <br>
<x-tab> </x-tab>pancréatalgie/NOM<br>
=============================================<br>
<br>
More details in<br>
<br>
<a href="http://www.univ-nancy2.fr/pers/namer/Publis/MEDINFO2004.doc" eudora="autourl">http://www.univ-nancy2.fr/pers/namer/Publis/MEDINFO2004.doc</a><br>
<br>
Unfortunately, it is still too soon to deliver a version of DeriF because
results have still to be validated.<br>
<br>
As soon as results for medical terminology are validated (i.e. in a few
months, at the end of the French national UMLF project, coordinated by P.
Zweigenbaum and supported by grants from the French Ministry of
Education), they will be made freely available for the scientific
community<br>
<br>
Greetings<br>
Fiammetta<br>
<br>
<br>
<br>
At 08:17 27/01/2005 -0600, John A Goldsmith a écrit:<br>
<br>
<font face="arial" size=2><blockquote type=cite cite>In connection with
the Linguistica project
(<a href="http://linguistica.uchicago.edu/">http://linguistica.uchicago.edu</a>
, and
<a href="http://linguistica.uchicago.edu/alchemist.html">http://linguistica.uchicago.edu/alchemist.html</a>
), we are in the process of building gold-standards of morphological
segmentation in a common XML format for a number of languages. Our
concern is more with morphological segmentation (and allomorphy) and less
with tagging of morphosyntactic features.<br>
</font><br>
<br>
<br>
I would very much appreciate pointers to any lists of words, in any
language, with an indication of correct morphological segmentation, or
pointers to software that does a good job of accomplishing this in
particular languages. <br>
<br>
<br>
<br>
Some morphological parsers focus on providing lemmatization or
morphosyntactic features, like Namer s FLEMM mentioned by Jean Véronis,
as far as I can tell; these do not help us with our task. In addition,
since our goal is to use these gold standards for testing, rather than
for training, accuracy is particularly important. <br>
<br>
<br>
<br>
I ll post a summary of all responses I receive. Thanks very much!<br>
<br>
<br>
<br>
John Goldsmith </blockquote></html>