Multi-label Text Classification with a Robust Label Dependent Representation
Automatic text classification is the task of assigning unseen documents to a predefined set of classes or categories. Text Representation for classification have been traditionally approached with tf.idf due to its simplicity and good performance. Multi-label automatic text classification has been traditionally tackled in the literature either by transforming the problem to apply binary techniques or by adapting binary algorithms to work with multiple labels. We present tf.rrfl, a novel text representation for the multilabel classification approach. Our proposal focuses on modifying the data set input to the algorithm, differentiating the input by the label to evaluate. Performance of tf.rrfl was tested with a known benchmark and compared to alternative techniques. The results show improvement compared to alternative approaches in terms of Hamming loss.
Multi-label Text classification Text representation Machine learning
Rodrigo Alfaro Héctor Allende
Departamento de Informática, Universidad Técnica Federico Santa María and Escuela de Ingeniería Info Departamento de Informática, Universidad Técnica Federico Santa María and Facultad de Ingeniería, Un
国际会议
桂林
英文
17-20
2010-11-17（万方平台首次上网日期，不代表论文的发表时间）