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

Takeshi Onishi ; Takuya Kadohira SAMURAI ORCID (National Institute for Materials ScienceROR) ; Ikumu Watanabe SAMURAI ORCID (National Institute for Materials ScienceROR)

Relation extraction with weakly supervised learning based on process structure property performance reciprocity.pdf
Download file (1.46 MB)
Download as zip (921 KB)
Collection

Citation
Takeshi Onishi, Takuya Kadohira, Ikumu Watanabe. Relationship Extraction with Weakly Supervised Learning Based on Process-Structure-Property-Performance Reciprocity. SCIENCE AND TECHNOLOGY OF ADVANCED MATERIALS. 2018, 19 (1), .
SAMURAI

Description:

(abstract)

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.

Rights:

Keyword: Natural language processing, knowledge extraction, relation extraction, weakly supervised learning, materials informatics

Date published: 2018-12-31

Publisher: Informa UK Limited

Journal:

  • SCIENCE AND TECHNOLOGY OF ADVANCED MATERIALS (ISSN: 14686996) vol. 19 issue. 1

Funding:

Manuscript type: Publisher's version (Version of record)

MDR DOI:

First published URL: https://doi.org/10.1080/14686996.2018.1500852

Related item:

Other identifier(s):

Contact agent:

Updated at: 2024-01-05 22:13:14 +0900

Published on MDR: 2023-02-17 09:32:02 +0900

Filename Size
Filename Relation extraction with weakly supervised learning based on process structure property performance reciprocity.pdf (Thumbnail)
application/pdf 		Size 1.46 MB Detail