Towards an Open Platform for Legal Information

Malte Ostendorff, Till Blume, Saskia Ostendorff

Abstract

Recent advances in the area of legal information systems have led to a variety of applications that promise support in processing and accessing legal documents. Unfortunately, these applications have various limitations, e.g., regarding scope or extensibility. Furthermore, we do not observe a trend towards open access in digital libraries in the legal domain as we observe in other domains, e.g., economics of computer science. To improve open access in the legal domain, we present our approach for an open source platform to transparently process and access Legal Open Data. This enables the sustainable development of legal applications by offering a single technology stack. Moreover, the approach facilitates the development and deployment of new technologies. As proof of concept, we implemented six technologies and generated metadata for more than 250,000 German laws and court decisions. Thus, we can provide users of our platform not only access to legal documents, but also the contained information.

Introduction

The legal domain is currently undergoing a digital transformation, yet it faces a significant obstacle: data silos. While powerful tools exist for processing legal text, most are commercial "black boxes"—expensive, country-specific, and closed-source. This lack of transparency prevents researchers and developers from accessing raw data, making it impossible to verify results or build innovative applications. Unlike fields such as computer science or economics, the legal world lacks a unified, open-access digital library. For "access to justice" to be a reality, the underlying data and the analytical tools must be democratized. The Open Legal Data Platform aims to break these proprietary silos by providing a standardized, end-to-end pipeline for transparent legal research.

System Architecture and Methodology

The authors propose a modular technology stack built on the Django framework, following a three-stage lifecycle: harvesting, processing, and service delivery.

The Open Legal Data Platform architecture, illustrating the flow from primary and linked open data through preprocessing to the central platform and user services.
  1. Harvesting: The platform aggregates primary data from official government sources (e.g., the German Federal Ministry of Justice) and secondary data from Linked Open Data (LOD) sources like Knowledge Graphs and Geo Data.
  2. Open Processing Pipeline: This core engine transforms raw text into structured data. Key components include reference extraction (using a hybrid rules/ML system), Named Entity Recognition (NER) via SpaCy, and automated keyword generation using TF-IDF and CF-IDF.
  3. Services: Processed data is served via a REST API and indexed using Elasticsearch for high-speed full-text search. A citation-based recommender system further assists users in finding related cases.

Dataset and Implementation

The platform hosts a significant new resource: a collection of over 250,000 German laws and court decisions. Beyond raw text, the platform provides rich metadata, including extracted entities and citation links. By adopting international standards like Akoma-Ntoso (an XML schema for legal documents), the platform is designed to be country-agnostic, facilitating future cross-jurisdictional expansion.

Insights and Results

The platform's value is most evident in its ability to reveal hidden patterns through metadata. By visualizing citation networks, researchers can gain insights into judicial behavior. For instance, frequent citations to procedural statutes like the VwGO often indicate procedural rejections rather than substantive legal shifts.

A visualization of the citation network among German federal courts, identifying the Federal Constitutional Court (Bundesverfassungsgericht) as a central hub.

Key results include the successful processing of a quarter-million legal documents and the integration of six core technologies into a single pipeline. The open dataset has already fueled innovation, such as "VizLaw," a visual query interface developed by independent developers that won a major legal tech hackathon.

Conclusion and Future Work

While the platform successfully demonstrates the power of open legal data, challenges remain. Current data is skewed toward federal courts due to more open publishing policies, potentially biasing large-scale analysis. Future work will focus on harvesting state-level data and improving "Legal Design" to make information more accessible to non-professionals. Ultimately, the Open Legal Data Platform serves as a "MediaWiki" for law—a common infrastructure for democratizing legal knowledge.

Summary updated

Abstract

Recent advances in the area of legal information systems have led to a variety of applications that promise support in processing and accessing legal documents. Unfortunately, these applications have various limitations, e.g., regarding scope or extensibility. Furthermore, we do not observe a trend towards open access in digital libraries in the legal domain as we observe in other domains, e.g., economics of computer science. To improve open access in the legal domain, we present our approach for an open source platform to transparently process and access Legal Open Data. This enables the sustainable development of legal applications by offering a single technology stack. Moreover, the approach facilitates the development and deployment of new technologies. As proof of concept, we implemented six technologies and generated metadata for more than 250,000 German laws and court decisions. Thus, we can provide users of our platform not only access to legal documents, but also the contained information.
BibTeX
@inproceedings{ostendorff2020towards,
  author = {Malte Ostendorff and Till Blume and Saskia Ostendorff},
  title = {{Towards an Open Platform for Legal Information}},
  booktitle = {JCDL},
  year = {2020},
  url = {https://openreview.net/forum?id=lFb0y5n0fvI},
}
Figure