Abstract

We consider the task of Extreme Multi-Label Text Classification (xmtc) in the legal domain. We release a new dataset of 57k legislative documents from eur-lex, the European Union’s public document database, annotated with concepts from eurovoc, a multidisciplinary thesaurus. The dataset is substantially larger than previous eur-lex datasets and suitable for xmtc, few-shot and zero-shot learning. Experimenting with several neural classifiers, we show that bigrus with self-attention outperform the current multi-label state-of-the-art methods, which employ label-wise attention. Replacing cnns with bigrus in label-wise attention networks leads to the best overall performance.