arxiv: 1906.02192 · v1 · pith:3OBRU62Cnew · submitted 2019-06-05 · 💻 cs.CL

Large-Scale Multi-Label Text Classification on EU Legislation

Ilias Chalkidis , Manos Fergadiotis , Prodromos Malakasiotis , Ion Androutsopoulos This is my paper

classification 💻 cs.CL

keywords textbertclassificationdocumentslarge-scalelearninglmtcmulti-label

0 comments p. Extension

Add this Pith Number to your LaTeX paper

\usepackage{pith}
\pithnumber{3OBRU62C}

Prints a linked pith:3OBRU62C badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

We consider Large-Scale Multi-Label Text Classification (LMTC) in the legal domain. We release a new dataset of 57k legislative documents from EURLEX, 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.

This paper has not been read by Pith yet.

discussion (0)

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

SynBench: A Benchmark for Differentially Private Text Generation
cs.AI 2025-09 conditional novelty 7.0

SynBench benchmarks DP text generators across nine datasets and uses a new MIA to show that public pre-training on portions of private data overestimates synthetic text quality and breaks DP privacy bounds.