Feature Construction for Relational Sequence Learning

Abstract. We tackle the problem of multi-class relational sequence learning using relevant patterns discovered from a set of labelled sequences. To deal with this problem, firstly each relational sequence is mapped into a feature vector using the result of a feature construction method. Since, the efficacy of sequence learning algorithms strongly depends on the features used to represent the sequences, the second step is to find an optimal subset of the constructed features leading to high classification accuracy. This feature selection task has been solved adopting a wrapper approach that uses a stochastic local search algorithm embedding a na¨ıve Bayes classifier. The performance of the proposed method applied to a real-world dataset shows an improvement when compared to other established methods, such as hidden Markov models, Fisher kernels and conditional random fields for relational sequences. Key words: Relational Sequence Learning, Feature Construction/Selection, Stochast...

• Type: Journal
• Year: 2010
• Where: CORR
• Authors: Nicola Di Mauro, Teresa Maria Altomare Basile, Stefano Ferilli, Floriana Esposito
• Keywords: CORR 2010, Education, Multi-class Relational Sequence, Relational Sequence, Stochastic Local Search