Publication

Relationship Extraction with Weakly Supervised Learning Based on Process-Structure-Property-Performance Reciprocity

MDR Open

We developed a computer aided material design system that extracts relationships from natural language texts in weakly labeled data. We believe that our study makes a significant contribution to the literature because we trained a machine learning model with minimal annotated relation data to extract relationships between scientific concepts from scientific articles.

First published at
Creator
Keyword
Resource type
Publisher
Rights statement
Language

Items