Extreme Multi-Label Legal Text Classification: A case study in EU Legislation

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 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.

arXiv comment10 pages, long paper at NLLP Workshop of NAACL-HLT 2019

References in corpus (6)

• Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
• Enriching Word Vectors with Subword Information
• Neural Machine Translation in Linear Time
• Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention
• LSHTC: A Benchmark for Large-Scale Text Classification
• Enhancing Navigation on Wikipedia with Social Tags

Cited by in corpus (2)

• DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents
• A Benchmark for Lease Contract Review