-
-
Autor*innen: Nam, Jinseok; Kim, Jungi; Loza Mencía, Eneldo; Gurevych, Iryna; Fürnkranz, Johannes
Titel: Large-scale multi-label text classification. Revisiting neural networks
Aus: Calders,Toon;Esposito,Floriana;Hüllermeier,Eyke;Meo, Rosa (Hrsg.): Machine learning and knowledge discovery in databases: European Conference, ECML PKDD 2014, Nancy, France, September 15-19, 2014. Proceedings, Part II, Berlin: Springer, 2014 (Lecture notes in Computer Science, 8725), S. 437-452
DOI: 10.1007/978-3-662-44851-9_28
URL: http://link.springer.com/chapter/10.1007/978-3-662-44851-9_28
Dokumenttyp: 4. Beiträge in Sammelwerken; Tagungsband/Konferenzbeitrag/Proceedings
Sprache: Englisch
Schlagwörter: Elektronische Bibliothek; Information Retrieval; Klassifikation; Lernen; Netzwerk; Ranking; Text
Abstract: Neural networks have recently been proposed for multi-label classification because they are able to capture and model label dependencies in the output layer. In this work, we investigate limitations of BP-MLL, a neural network (NN) architecture that aims at minimizing pairwise ranking error. Instead, we propose to use a comparably simple NN approach with recently proposed learning techniques for large-scale multi-label text classification tasks. In particular, we show that BP-MLL's ranking loss minimization can be efficiently and effectively replaced with the commonly used cross entropy error function, and demonstrate that several advances in neural network training that have been developed in the realm of deep learning can be effectively employed in this setting. Our experimental results show that simple NN models equipped with advanced techniques such as rectified linear units, dropout, and AdaGrad perform as well as or even outperform state-of-the-art approaches on six large-scale textual datasets with diverse characteristics. (DIPF/Org.)
DIPF-Abteilung: Informationszentrum Bildung