%Aigaion2 BibTeX export from Knowledge Engineering Publications
%Monday 27 May 2019 11:00:50 AM

@INPROCEEDINGS{jf:ECML-PKDD-08,
     author = {Loza Menc{\'{\i}}a, Eneldo and F{\"{u}}rnkranz, Johannes},
     editor = {Daelemans, Walter and Goethals, Bart and Morik, Katharina},
      month = sep,
      title = {Efficient Pairwise Multilabel Classification for Large-Scale Problems in the Legal Domain},
  booktitle = {Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Disocvery in Databases (ECML-PKDD-2008), Part II},
     series = {Lecture Notes in Computer Science},
     volume = {5212},
       year = {2008},
      pages = {50--65},
  publisher = {Springer},
    address = {Antwerp, Belgium},
       note = {accompanying EUR-Lex dataset available at \url{http://www.ke.tu-darmstadt.de/resources/eurlex}},
       isbn = {978-3-540-87480-5},
        url = {http://www.ke.tu-darmstadt.de/publications/papers/ECML08.pdf},
        doi = {10.1007/978-3-540-87481-2_4},
   abstract = {In this paper we applied multilabel classification algorithms to the EUR-Lex database of legal documents of the European Union. On this document collection, we studied three different multilabel classification problems, the largest being the categorization into the EUROVOC concept hierarchy with almost 4000 classes.
We evaluated three algorithms: (i) the binary relevance approach which independently trains one classifier per label; (ii) the multiclass multilabel perceptron algorithm, which respects dependencies between the base classifiers; and (iii) the multilabel pairwise perceptron algorithm, which trains one classifier for each pair of labels.
All algorithms use the simple but very efficient perceptron algorithm as the underlying classifier, which makes them very suitable for large-scale multilabel classification problems. The main challenge we had to face was that the almost 8,000,000 perceptrons that had to be trained in the pairwise setting could no longer be stored in memory. We solve this problem by resorting to the dual representation of the perceptron, which makes the pairwise approach feasible for problems of this size.
The results on the EUR-Lex database confirm the good predictive performance of the pairwise approach and demonstrates the feasibility of
this approach for large-scale tasks.}
}