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 EURLEX, the European Union's public document database, annotated with concepts from EUROVOC, a multidisciplinary thesaurus. The dataset is substantially larger than previous EURLEX 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.
@article{arxiv.1905.10892,
title = {Extreme Multi-Label Legal Text Classification: A case study in EU Legislation},
author = {Ilias Chalkidis and Manos Fergadiotis and Prodromos Malakasiotis and Nikolaos Aletras and Ion Androutsopoulos},
journal= {arXiv preprint arXiv:1905.10892},
year = {2019}
}
Comments
10 pages, long paper at NLLP Workshop of NAACL-HLT 2019