MinScIE: Citation-centered Open Information Extraction
Anne Lauscher, Yide Song, Kiril Gashteovski
Abstract
Acknowledging the importance of citations in scientific literature, in this work we present MinScIE, an Open Information Extraction system which provides structured knowledge enriched with semantic information about citations. By comparing our system to it’s original core, MinIE, we show that our approach improves extraction precision by 3 percentage points.
Related Papers
ChatPD: An LLM-driven Paper-Dataset Networking System2025-05-28Long-context Non-factoid Question Answering in Indic Languages2025-04-18Few-shot Continual Relation Extraction via Open Information Extraction2025-02-23Testing Prompt Engineering Methods for Knowledge Extraction from Text2025-02-18Challenges in Expanding Portuguese Resources: A View from Open Information Extraction2025-01-21Neon: News Entity-Interaction Extraction for Enhanced Question Answering2024-11-19$\textit{BenchIE}^{FL}$ : A Manually Re-Annotated Fact-Based Open Information Extraction Benchmark2024-07-23Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs2024-06-27