Adaptation of two-level morphology for use in a real world application

Stefan Raeymaekers, Tom Mahieu, Karel De Vlaminck, Gerda Janssens, Wouter Joosen 
 

We are working on a module for morpholgical analysis and generation, 
which is based upon Two-Level Morphology(TLM).  This module is situated
within a bigger project to improve an existing real world application.  
 

The purpose of this paper is to enlighten our approach to some problems 
or holes we encountered with the original TLM-system described by 
Koskenniemi.  We also present the formalism we use to encode the lexica.
 

The requirements of the system are amongst others:
- Enabling to exclude or compel combinations of prefixes and suffixes on 
  the same wordform.
- Providing an elegant way to add compound words to the lexica.
- The generation should start from the canonical form and some supplied 
  lexical features instead of starting from a concatenation of lexical 
  morphemes, that the user has composed beforehand.
- Adaptation at runtime of both the two-level rules and the lexica.



Contact Person:

Stefan Raeymaekers

K.U. Leuven

Departement Computerwetenschappen

Celestijnenlaan 200A

B-3001 Heverlee

Phone: +32 16 327638

E-mail: stefan.raeymaekers@cs.kuleuven.ac.be