Data-driven materials research enabled by natural language processing and information extraction
Исследования материалов на основе данных, обеспечиваемые обработкой естественного языка и извлечением информации
2020-12-01
SCID: 54.1/jjd2hpwj
Discuss with AI
data-driven materials researchinformation extractionmaterials science literaturenatural language processingtext mining
Figures from the paper
Abstract (AI)
Given the emergence of data science and machine learning throughout all aspects of society, but particularly in the scientific domain, there is increased importance placed on obtaining data. Data in materials science are particularly heterogeneous, based on the significant range in materials classes that are explored and the variety of materials properties that are of interest. This leads to data that range many orders of magnitude, and these data may manifest as numerical text or image-based information, which requires quantitative interpretation. The ability to automatically consume and codify the scientific literature across domains—enabled by techniques adapted from the field of natural language processing—therefore has immense potential to unlock and generate the rich datasets necessary for data science and machine learning. This review focuses on the progress and practices of natural language processing and text mining of materials science literature and highlights opportunities for extracting additional information beyond text contained in figures and tables in articles. We discuss and provide examples for several reasons for the pursuit of natural language processing for materials, including data compilation, hypothesis development, and understanding the trends within and across fields. Current and emerging natural language processing methods along with their applications to materials science are detailed. We, then, discuss natural language processing and data challenges within the materials science domain where future directions may prove valuable.
Key Findings
1
Extracting quantitative information from figures and tables offers important opportunities beyond conventional text-based literature mining.
2
Materials-science data are highly heterogeneous, spanning diverse material classes, properties, scales, and numerical or image-based representations.
3
Natural language processing and information extraction can automatically codify scientific literature to generate datasets for materials data science and machine learning.
4
Text mining of materials literature supports data compilation, hypothesis development, and identification of trends within and across research fields.
5
The review identifies ongoing methodological and data challenges that must be addressed to advance NLP applications in materials science.
Research Object
materials science literature and its embedded scientific data
Research Subject
the progress, practices, applications, and challenges of natural language processing and information extraction for compiling, interpreting, and discovering materials-science data
Publication Details
Publication Date
2020-12-01
Journal
Publisher
ISSN
Cited by
325
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai5
Rethinking the Inception Architecture for Computer Vision2016
Distributed Representations of Words and Phrases and their Compositionality2013
The FAIR Guiding Principles for scientific data management and stewardship2016
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation2013
Enriching Word Vectors with Subword Information2017