URL:
<http://gna.org/task/?4812>
Summary: Submission of Empirical Morphological Reasoning
Project: Gna! Administration
Submitted by: tarnold
Submitted on: Dienstag 20.02.2007 um 14:19
Status: None
Approval Status: None
Should Start On: Dienstag 20.02.2007 um 00:00
Should be Finished on: Freitag 02.03.2007 um 00:00
Category: Project Approval
Priority: 5 - Normal
Privacy: Public
Assigned to: None
Open/Closed: Open
Discussion Lock: Any
_______________________________________________________
Details:
A new project has been registered at Gna!
This project account will remain inactive until a site admin approves or
discards the registration.
= Registration Administration =
While this item will be useful to track the registration process, *approving
or discarding the registration must be done using the specific Group
Administration <https://gna.org/siteadmin/groupedit.php?group_id=2089> page*,
accessible only to site administrators, effectively *logged as site
administrators* (superuser):
* Group Administration
<https://gna.org/siteadmin/groupedit.php?group_id=2089>
= Registration Details =
* Name: *Empirical Morphological Reasoning*
* System Name: *emores*
* Type: Programs
* License: GNU General Public License V2 or later
----
==== Description: ====
emores source distribution:
http://mypage.bluewin.ch/tarnold/emores/emores-0.0.1.tar.bz2
emores documentation (draft):
http://mypage.bluewin.ch/tarnold/emores/emores.pdf
The aim of emores, an Empirical MOrphological REaSoning system, is to
facilitate a guided brute force attack on a specific problem of language
morphology: extending the lexicon from corpus data. For a particular
inflected natural language, it requires a hand crafted SFST finite state
transducer and a seed lexicon covering all of its regular inflection classes.
When fed with new word forms, it guesses which lemmas could have generated it
(induction) and what other word forms could be explained with that lemmas
(deduction). If all possible word forms for a guessed lemma are found in the
data, the lemma counts as saturated and is asserted as a new lexical entry.
The emores project is still in experimental stage. One of the unresolved
problems is the fact that for real size natural language morphologies like
SMOR, the deduction step seems not to be feasible due to infinite
overgeneration. Even the induction step for the XMOR toy morphology suffers
from some overgeneration. Further work will show if and how these problems
can be overcomed.
==== Other Software Required: ====
Runtime:
pysfst / http://home.gna.org/pysfst/ / GPL-2
SFST / http://www.ims.uni-stuttgart.de/projekte/gramotron/SOFTWARE/SFST.html
/ GPL-2
python / http://www.python.org/ / PSF-2.2 (GPL compatible)
postgresql / http://www.postgresql.org / POSTGRESQL (GPL compatible)
sqlalchemy / http://www.sqlalchemy.org / MIT (GPL compatible)
psycopg2 / http://www.initd.org/projects/psycopg2 / GPL-2
Build time:
dia / http://www.gnome.org/projects/dia/ / GPL-2
tedia2sql / http://tedia2sql.tigris.org / GPL-2
Documentation only (LaTeX GPL-incompatibility should be no issue):
latex / http://tug.org/teTeX/ / LPPL (not GPL compatible)
glossary / http://theoval.cmp.uea.ac.uk/~nlct/ / LPPL (not GPL compatible)
==== Other Comments: ====
Emores is based on my psfst project already hosted by Gna!
_______________________________________________________
Reply to this item at:
<http://gna.org/task/?4812>
_______________________________________________
Nachricht geschickt von/durch Gna!
http://gna.org/
_______________________________________________
Register mailing list
[email protected]
https://mail.gna.org/listinfo/register
