Relaxation-Labelling Constraint Grammar File

The syntax of the file is based on that of Constraint Grammars [KVHA95], but simplified in many aspects, and modified to include weighted constraints.

An initial file based on statistical constraints may be generated from a tagged corpus using the src/utilities/train-tagger/bin/TRAIN.sh script provided with FreeLing. Later, hand written constraints can be added to the file to improve the tagger behaviour.

The file consists of two sections: SETS and CONSTRAINTS.



Subsections

Lluís Padró 2013-09-09