Sources of Evidence for Automatic Indexing of Political Texts

  title={Sources of Evidence for Automatic Indexing of Political Texts},
  author={M. Dehghani and H. Azarbonyad and maarten marx and J. Kamps},
  • M. Dehghani, H. Azarbonyad, +1 author J. Kamps
  • Published in ECIR 2015
  • Computer Science
  • Political texts on the Web, documenting laws and policies and the process leading to them, are of key importance to government, industry, and every individual citizen. Yet access to such texts is difficult due to the ever increasing volume and complexity of the content, prompting the need for indexing or annotating them with a common controlled vocabulary or ontology. In this paper, we investigate the effectiveness of different sources of evidence—such as the labeled training data, textual… CONTINUE READING
    8 Citations


    Automatic annotation of multilingual text collections with a conceptual thesaurus
    • 100
    • PDF
    The JRC-Acquis: A Multilingual Aligned Parallel Corpus with 20+ Languages
    • 601
    • Highly Influential
    • PDF
    JRC Eurovoc Indexer JEX - A freely available multi-label categorisation tool
    • 38
    • Highly Influential
    • PDF
    AdaRank: a boosting algorithm for information retrieval
    • 797
    • PDF
    Hierarchical multi-label classification of social text streams
    • 41
    • PDF
    Multilabel classification with meta-level features
    • 81
    • PDF
    Kernel-Based Learning of Hierarchical Multilabel Classification Models
    • 279
    • PDF
    Consistency in the selection of search concepts and search terms
    • 22
    Large-Scale Multi-label Text Classification - Revisiting Neural Networks
    • 226
    • PDF
    Training linear SVMs in linear time
    • 2,009
    • Highly Influential
    • PDF