starling

STARLING

Project information
Abstract: 

This project wants to investigate how techniques of statistical relational learning can be used for natural language processing. The focus will be on challenging natural language processing tasks, such as semantic role labeling, where syntac and semantic depedencies, structured and unstructured data, local and global models, and probabilistic and logical information must be combined with one another. For what concerns statistical relational learning, the emphasis will lie on probabilistic extensions of the programming language Prolog. The project does not only aim at obtaining improved natural language processing techniques but also better algorithms and systems for statistical relational learning.

Period: 
01/09/2010 - 31/01/2013
Sponsor(s): 

FWO

Sequence translation

This demo is an implementation of a sequence alignment script.

The input is two collections of sequences, viz. tokens and tags. Each sequence in the collection of tokens is paired with a sequence from the collection of tags. The order of the elements of a sequence can be random and is not used by the algorithm.

Feature-label association

Van Asch, V., & Daelemans W. (2013).  An analytical approach to similarity measure selection for selftraining. BENELEARN 2013: Proceedings of the 22nd Belgian-Dutch Conference on Machine Learning. 8-17. PDF
Verbeke, M., Van Asch V., Morante R., Frasconi P., Daelemans W., & Raedt L. D. (2012).  A Statistical Relational Learning Approach to Identifying Evidence Based Medicine Categories. Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. 579-589. PDF
Syndicate content