Difference between revisions of "Learning Constraint Grammars"

From Apertium
Jump to navigation Jump to search
 
(One intermediate revision by one other user not shown)
Line 4: Line 4:
== Statistical approach ==
== Statistical approach ==


In statistical approach Constraint Grammar style rules are learned by calculating n-gram probabilities of word and part-of-speech tag groups. Current work on implementing such a system is at [https://github.com/nuboro/CG_module/ nuboro's Github repository], and it is based on the paper [https://archive.org/details/arxiv-cmp-lg9607002 Inducing Constraint Grammars].
In statistical approach Constraint Grammar style rules are learned by calculating n-gram probabilities of word and part-of-speech tag groups. Current work on implementing such a system is at [https://github.com/nuboro/CG-generator nuboro's Github repository], and it is based on the paper [https://archive.org/details/arxiv-cmp-lg9607002 Inducing Constraint Grammars].


== Machine Learning ==
== Machine Learning ==
Line 13: Line 13:
* http://swarm.cs.pub.ro/~asfrent/msc/thesis.pdf – Inductive Logic Programming
* http://swarm.cs.pub.ro/~asfrent/msc/thesis.pdf – Inductive Logic Programming
* http://ucrel.lancs.ac.uk/acl/C/C98/C98-2123.pdf – Inductive Logic Programming
* http://ucrel.lancs.ac.uk/acl/C/C98/C98-2123.pdf – Inductive Logic Programming

[[Category:Constraint Grammar]]

Latest revision as of 22:59, 25 December 2016

Constraint Grammar style part-of-speech disambiguation rules can be learned automatically from disambiguated parallel corpora.


Statistical approach[edit]

In statistical approach Constraint Grammar style rules are learned by calculating n-gram probabilities of word and part-of-speech tag groups. Current work on implementing such a system is at nuboro's Github repository, and it is based on the paper Inducing Constraint Grammars.

Machine Learning[edit]

A subfield of Machine Learning, called Inductive Logic Programming, has been used to learn Constraint Grammar style disambiguation rules. See for example the branch mil-pos-tagger.

Papers[edit]