LexNLP
softwareNatural language processing and information extraction for legal and regulatory text
period: 2018-2021
tech:
Natural Language ProcessingLegal Informatics
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
LexNLP is an open source Python package for natural language processing and machine learning for legal and regulatory text. It provides pre-trained models and utilities for:
Key Features
- Information Extraction: Extract citations, dates, definitions, durations, money, regulations, and more
- Document Segmentation: Split documents into sentences, paragraphs, and sections
- Classification: Pre-trained classifiers for contract types and clauses
- Text Cleaning: Normalize legal text and handle OCR errors
Impact
LexNLP has been used by law firms, legal tech companies, and researchers worldwide for various applications including:
- Contract analysis and due diligence
- Regulatory compliance monitoring
- Legal research automation
- Document review workflows
The library was acquired as part of the LexPredict acquisition in 2018 and continues to be maintained as an open source project.
Related Work
- Paper: LexNLP: Natural language processing and information extraction for legal and regulatory texts
- Published in Research Handbook on Big Data Law (2021)