%Aigaion2 BibTeX export from Knowledge Engineering Publications
%Saturday 18 September 2021 12:23:19 PM

     author = {Loza Menc{\'{\i}}a, Eneldo and F{\"{u}}rnkranz, Johannes},
     editor = {Francesconi, Enrico and Montemagni, Simonetta and Peters, Wim and Tiscornia, Daniela},
   keywords = {EUR-Lex Database, learning by pairwise comparison, Legal Documents, multilabel classification, Text Classification},
      month = may,
      title = {Efficient Multilabel Classification Algorithms for Large-Scale Problems in the Legal Domain},
  booktitle = {Semantic Processing of Legal Texts -- Where the Language of Law Meets the Law of Language},
    edition = {1},
     series = {Lecture Notes in Artificial Intelligence},
     volume = {6036},
       year = {2010},
      pages = {192-215},
  publisher = {Springer-Verlag},
       note = {accompanying EUR-Lex dataset available at \url{http://www.ke.tu-darmstadt.de/resources/eurlex}},
       isbn = {978-3-642-12836-3},
        url = {http://www.ke.tu-darmstadt.de/publications/papers/loza10eurlex.pdf},
        doi = {10.1007/978-3-642-12837-0_11},
   abstract = {In this paper we apply multilabel classification algorithms to the EUR-Lex database of legal documents of the European Union. For 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.}