Challenges in Information-Mining the Materials Literature: A Case Study and Perspective
Challenges in Information-Mining the Materials Literature: A Case Study and Perspective
复制标题
材料文献信息挖掘的挑战：案例研究和视角
DOI：
10.1021/acs.chemmater.2c00445
复制
发表时间：
2022
影响因子：
8.6
通讯作者：
Risko, Chad
中科院分区：
文献类型：
--
作者：
Smith, Andrew;Bhat, Vinayak;Ai, Qianxiang;Risko, Chad
机器学习 (ML) 技术在材料科学中的快速发展和应用催生了用于机器驱动和自主/高通量材料设计和发现的新工具。此外，利用自然语言处理 (NLP) 算法从已发表文献中的传统实验中提取数据的努力，为这些计算机设计和发现工作提供了开发大量数据库的机会。虽然NLP应用于社会的各个方面，但其在材料科学中的应用仍处于非常早期的阶段。该视角提供了应用 NLP 提取有机材料制备相关信息的案例研究。我们在基础层面上介绍案例研究，旨在与来自不同科学背景的研究人员讨论这些技术和流程。我们还讨论了案例研究中面临的挑战，并提供了评估，以在社区贡献的帮助下提高材料科学 NLP 技术的准确性。
The rapid development and application of machine learning (ML) techniques in materials science have led to new tools for machine-enabled and autonomous/high-throughput materials design and discovery. Alongside, efforts to extract data from traditional experiments in the published literature with natural language processing (NLP) algorithms provide opportunities to develop tremendous data troves for thesein silicodesign and discovery endeavors. While NLP is used in all aspects of society, its application in materials science is still in the very early stages. This perspective provides a case study on the application of NLP to extract information related to the preparation of organic materials. We present the case study at a basic level with the aim to discuss these technologies and processes with researchers from diverse scientific backgrounds. We also discuss the challenges faced in the case study and provide an assessment to improve the accuracy of NLP techniques for materials science with the aid of community contributions.