Skip to content

Legal-writing case study corpus: over 16,000 documents yielding a knowledge graph of over 55 million RDF triplets

Design · All designs
Evidence · no claims cited

Description

The case study applied YAI4Edu to 22 pages excerpted from the textbook "United States Legal Language and Culture" (Brostoff & Sinsheimer, 2013), 5,407 open access web pages from the Legal Information Institute encyclopedia and Wikipedia, and 11,198 legal cases on PTSD disability claims from the Board of Veterans' Appeals. Altogether 16,606 documents yielded 1,309,463 extracted questions and a knowledge graph whose total size was 55,046,923 RDF triplets (Table 1). The material supports teaching how to write a legal memorandum for a veteran's PTSD disability claim.

Design Implications

Context

Requirements

  • About ten manually added RDF triplets were needed to fill identified knowledge gaps such as "memo" being a synonym for "memorandum"

Constraints

  • The whole extracted RDF graph was not thoroughly analyzed, so other knowledge gaps may yet emerge

Target Learners

  • Students in the University of Pittsburgh course Applied Legal Analytics and AI

Learning Goals

  • Writing legal memoranda, using statutes, reading and synthesizing cases, and making arguments with concrete cases

Claims

  • Yai4Edu Explanatory Textbook Pipeline

Examples

-

Key Sources

  • Sovrano Francesco, Ashley Kevin, Brusilovsky Peter Leonid, Vitali Fabio. (2024). How to Improve the Explanatory Power of an Intelligent Textbook: a Case Study in Legal Writing. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-024-00399-w
Page metadata
Field Value
type design
id legal-writing-case-study-corpus
title Legal-writing case study corpus: over 16,000 documents yielding a knowledge graph of over 55 million RDF triplets
description The case study applied YAI4Edu to 22 pages excerpted from the textbook "United States Legal Language and Culture" (Brostoff & Sinsheimer, 2013), 5,407 open access web pages from the Legal Information Institute encyclo...
status review
generated by process:settle-candidates on 2026-10-27
trust unverified — no one has confirmed this page's content
sources 1 — sovrano-francesco-2024

Frontmatter is the page's machine-readable record — see the Schema & Guide.