Legal Text Analytics

A list of selected resources, methods, and tools dedicated to Legal Text Analytics.

Please read the contribution guidelines before contributing. Please add a resource by raising a pull request. We also seek for discussion and proposal of new ideas (including additional content sections) as issues.

Contents

• Selected Tasks and Use Cases
• Methods
• Libraries
• Datasets and Data
• Large Language Models and GPT
• Annotation and Data Schemes
• Annotation Tools
• Software (interfaces)
• Research Groups and Labs
• Tutorials

• Credits

Selected Tasks and Use Cases

Back to Top

• Optical Character Recognition (find more information here)
• Legal Document Pre-processing (find more information here)
• Clause Segmentation and Sentence Boundary Detection
• Information Extraction and Named Entity Recognition (find more information here)
• Legal Norm Classification
• Machine Translation
• Document Comparison and Semantic Matching
• Text Summarization
• Argument Mining
• Question Answering
• Legal Case Outcome Prediction
• Legal and Regulatory Monitoring
• Legal Criticality Prediction
• Court View Generation
• Reference and Coreference Extraction
• Document Assembling and Generation
• Voice Transcription
• Anomaly Detection
• Data Anonymization
• Consistency Checking
• Natural Language Processing in the Legal Domain

Methods

Back to Top

• NLP Progress
• Text Visualizations
• Optical Character Recognition
• Rule-based methods for NLP, Apache Ruta, Jape Grammar
• Statistical NLP
• Machine Learning Frameworks
• Neural networks and deep learning for NLP Tutorial
• Domain adaptation (e.g., research paper)

Libraries

Back to Top

• Spacy - Industrial-Strength Natural Language Processing
• Scikit - machine learning in python
• NLTK - Natural Language Toolkit
• Apache UIMA
• Gate - General Architecture for Text Engineering
• Hugging Face - more than 1000 pre-trained transformer/embedding models for the legal domain
• German Bert Model: Deepset AI
• Flair - SOTA NLP (incl. biomedical and legal data)
• Blackstone - Legal Named Entity Recognition and Text Categorizer
• Legal Reference Detection - Neo Search
• Legal Reference Detection - Open Legal Data
• Haystack - Transformers at scale for question answering & neural search
• Sentence Boundary Detection (US Caselaw)
• Quantitative Legal Studies
• CiteURL - an extensible tool to detect and hyperlink legal citations
• LexNLP – Python NLP library for legal text analytics
• Dutch Case Law Extractor - Functions to obtain published Dutch case law (rechtspraak) data and available metadata associated to the cases
• Case Law Explorer - Materials for building a network analysis software platform for analyzing Dutch and European court decisions

Datasets and Data

Back to Top

• NLP Datasets
• An 800GB Dataset of Diverse Text for Language Modeling
• Meta Search: Google Dataset Search
• OpenLegalData
• IR Ad-hoc Ranking Benchmarks, Training Datasets, etc.
• Belgium: Belgian Statutory Article Retrieval Dataset (BSARD), including code
• Awesome German NLP
• German Dataset for Legal Information Retrieval (GerDaLIR)
• Legal Entity Recognition
• Legal Text Summarization
• Legal Text Translation
• Legal Document Classification
• Legal Sentence Classification (German)
• 100k German Court Decisions
• Legal Paper Datasets
• LexGLUE: a Benchmark Dataset for Legal Language Understanding in English
• LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain
• MultiLegalPile: A 689GB Multilingual Legal Corpus
• MultiLegalSBD: A Multilingual Legal Sentence Boundary Detection Dataset
• MultiLegalNeg
• Awesome Legal Data
• Germany: Gesetze im Internet, Rechtsprechung im Internet, Verwaltungsvorschriften im Internet
• Germany: Annotated Court Decisions (Judgment style)
• Germany: German Federal Courts Dataset
• Germany: Quantitative dataset of asylum court hearings at German administrative courts. ASYFAIR
• Germany: Answering legal questions from laymen in German civil law system: Data and code. EACL Paper 2024
• Germany: Detecting void clauses in German standard form consumer contracts
• Germany: Aktenzeichen der Bundesrepublik Deutschland (AZ-BRD)
• Germany: Corpus des Deutschen Bundesrechts (C-DBR)
• Germany: Corpus der Entscheidungen des Bundesverfassungsgerichts (CE-BVerfG)
• Germany: Corpus der amtlichen Entscheidungssammlung des Bundesverfassungsgerichts (C-BVerfGE)
• Germany: Corona-Rechtsprechung des Bundesverfassungsgerichts (BVerfG-Corona)
• Germany: Corpus der Entscheidungen des Bundesverwaltungsgerichts (CE-BVerwG)
• Germany: Corpus der Entscheidungen des Bundesarbeitsgerichts (CE-BAG)
• Germany: Corpus der Entscheidungen des Bundespatentgerichts (CE-BPatG)
• Germany: Corpus der Entscheidungen des Bundesgerichtshofs (CE-BGH)
• Germany: Presidents and Vice-Presidents of the Federal Courts of Germany (PVP-FCG)
• Germany: Stoppwörter der Deutschen Rechtssprache (SW-DE-RS)
• France: The French Court Decision Structure dataset — FCD12K
• Switzerland: Swiss Legislation Corpus French and German
• Switzerland: Swiss Federal Supreme Court Dataset (SCD)
• Switzerland: Swiss Judgment Prediction
• Switzerland: Swiss Judgment Prediction XL
• Switzerland: Swiss Criticality Prediction
• Switzerland: Swiss Law Area Prediction
• Switzerland: Swiss Leading Decisions
• Switzerland: Swiss Legislation
• Switzerland: Swiss Rulings
• Switzerland: Swiss Leading Decision Summarzation
• Switzerland: Swiss Citation Extraction
• Switzerland: Swiss Court View Generation
• Switzerland: Swiss Doc2Doc Information Retrieval
• Turkey: Prediction of Outcomes in the Higher Courts of Turkey
• India: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation
• ECtHR: Judicial Decisions of the European Court of Human Rights
• ECtHR: LaCour!: Enabling Research on Argumentation in Hearings of the European Court of Human Rights
• ECtHR: Argument Mining Corpus
• EU Law (eurlex R Package), Digital Corpus of the European Parliament (DCEP)
• EU Regulatory Compliance Information Retrieval
• EU LEXTREME
• Israel: The Israeli Supreme Court Database
• Canada: Federal Laws and Regulations (ftp://205.193.86.89/)
• UK: UK Law Reports & Case Law Search
• UK: Cambridge Law Corpus
• Australia: Open Australian Legal Corpus — The first and only multijurisdictional open corpus of Australian legislative and judicial documents
• US Statutory Law Interpretation Data Set
• US Caselaw Sentence Boundary Detection Dataset
• US Caselaw Functional and Issue Specific Segmentation Dataset
• US Caselaw Sentence Polarity Detection
• US Caselaw Access Project
• US Federal caselaw via CourtListener RECAP by the Free.Law project, includes an API
• US Supreme Court Database
• US House of Representatives Office of the Law Revision Counsel
• US Board of Veterans Appeals (BVA) Citation Prediction Dataset and Code
• Overview of Political Science Datasets: PolData
• International Law: Text of Trade Agreements (ToTA)
• International Law: Corpus of Decisions: International Court of Justice (CD-ICJ)
• International Law: Corpus of Decisions: Permanent Court of International Justice (CD-PCIJ)
• United Nations: United Nations General Debate Corpus, United Nations Parallel Corpus
• Contract Understanding Atticus Dataset by The Atticus Project: A corpus of 13,000+ labels in 510 commercial legal contracts with rich expert annotations.
• Kira Systems M&A Dataset by Kira Systems: A non-commercial use dataset comprising 4,400 documents and labels for 50 legal concepts in the M&A Due Diligence setting.
• India: ILSI Dataset for Legal Statute Identification
• India: Dataset for Semantic Segmentation / Rhetorical Role Labeling
• India: Summarization with Multiple Datasets
• India: BUILDNyAI
• European Patent Office - EP full-text data for text analytics
• Google Patents Public Datasets: connecting public, paid, and private patent data
• World Patent Information (WPI) - Documents technical domains from the major patenting authorities
• Genocide Transcript Corpus (GTC)

Large Language Models and GPT

Back to Top

• See dedicated repository on Large Language Models (LLMs) and Generative Pre-trained Transformers (GPTs) for Legal
• ChatGPT at OpenAI: Examples, Documentation, Pricing, Fine-tuning ChatGPT
• Sketch summarizing ChatGPT
• Large Language Models: Report by KI Bundesverband
• Large Language Models: Hugging Face Report
• Report on Limitations of ChatGPT
• GPT Takes the Bar Exam
• Legal Language Models

Annotation and Data Schemes

Back to Top

• Annotation guidelines for Legal Entity Recognition (Germany)
• Semantic Types of Legal Norms
• Annotation Guidelines for Sentence Boundary Detection in Caselaw (US)
• Annotation Guidelines for Sentence Value in Statutory Interpretation (US)
• SALI: Modern Legal Industry Standards

Annotation Tools

Back to Top

• Awesome data annotation
• Prodigy
• Doccano
• Brat

Software (interfaces)

Back to Top

• Case Law Explorer - Network analysis software platform for analyzing Dutch and European court decisions - User Guide
• Electronic Database on Investment Treaties (EDIT)
• GraphDoc - User-friendly graphical interface that allows building decision trees - codebase
• gesp - Download all publicly available German court decisions straight from your terminal

Research Groups, Labs, and Communities

Back to Top

• Stanford University - CodeX: The Stanford Center for Legal Informatics
• Technical University of Munich
• Technical University of Munich - Legal Tech Group
• Bucerius Center on the Legal Profession
• Suffolk Law School - Legal Innovation & Technology (LIT) Lab
• University of Ottawa - Legal Technology Lab
• University of Vienna - Department of Innovation and Digitalisation in Law
• University of Amsterdam - Leibniz Center for Law
• University of Helsinki - LegalTech Research Lab
• Hofstra University - Law, Logic & Technology Research Laboratory
• Computational Legal Studies
• CIRSFID-AI – University of Bologna
• IAAIL - International Association for AI and Law
• ASAIL - Automated Detection, Extraction and Analysis of Semantic Information in Legal Texts
• Workshop on Natural Legal Language Processing: Papers, models, data sets, and related events
• Chinese AI and Law (CAIL)
• University of Copenhagen, iCourts, the Danish National Research Foundation's Centre of Excellence for International Courts
• Maastricht Law and Tech Lab

Tutorials

Back to Top

• Monkey Learn - Text Analysis
• Using NLP to understand laws
• Document Representation for Legal Texts
• Data Science for Lawyers - Learning Resources
• Coding for Lawyers (discontinued)
• Custom NLP Approaches to Data Anonymization
• Information Extraction in legal documents
• Legal NLP: Sentence classification and Explainable AI
• Legal AI Glossary
• Legal AI Learning Centre

Credits

Back to Top

Many thanks to our contributors and many more.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.