Word Embeddings for Multi-label Document Classification
In this paper, we analyze and evaluate word embeddings for representation of longer texts in the multi-label classification scenario. The embeddings are used in three convolutional neural network topologies. The experiments are realized on the Czech {\v{C}}TK and English Reuters-21578 standard corpora. We compare the results of word2vec static and trainable embeddings with randomly initialized word vectors. We conclude that initialization does not play an important role for classification. However, learning of word vectors is crucial to obtain good results.
PDF Abstract