Optimizing Probabilistic Models for Relational Sequence Learning [chapter]

Nicola Di Mauro, Teresa M. A. Basile, Stefano Ferilli, Floriana Esposito
2011 Lecture Notes in Computer Science  
This paper tackles the problem of relational sequence learning selecting relevant features elicited from a set of labelled sequences. Each relational sequence is firstly mapped into a feature vector using the result of a feature construction method. The second step finds an optimal subset of the constructed features that leads to high classification accuracy, by adopting a wrapper approach that uses a stochastic local search algorithm embedding a Bayes classifier. The performance of the
more » ... method on a real-world dataset shows an improvement compared to other sequential statistical relational methods, such as Logical Hidden Markov Models and relational Conditional Random Fields.
doi:10.1007/978-3-642-21916-0_27 fatcat:ooonnvoixbekflc5geb5lg6tri