This work releases a new dataset of 57k legislative documents from EUR-LEX, annotated with ∼4.3k EUROVOC labels, suitable for LMTC, few- and zero-shot learning, and shows that BIGRUs with label-wise attention perform better than other current state of the art methods.
We consider Large-Scale Multi-Label Text Classification (LMTC) in the legal domain. We release a new dataset of 57k legislative documents from EUR-LEX, annotated with ∼4.3k EUROVOC labels, which is suitable for LMTC, few- and zero-shot learning. Experimenting with several neural classifiers, we show that BIGRUs with label-wise attention perform better than other current state of the art methods. Domain-specific WORD2VEC and context-sensitive ELMO embeddings further improve performance. We also find that considering only particular zones of the documents is sufficient. This allows us to bypass BERT’s maximum text length limit and fine-tune BERT, obtaining the best results in all but zero-shot learning cases.
Manos Fergadiotis
5 papers