arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2009.06819cs.CL
收藏

MatScIE:一个自动化工具,用于生成计算材料科学文献中使用的方法和参数数据库

MatScIE: An automated tool for the generation of databases of methods and parameters used in the computational materials science literature

Indian Institute of Technology, Kharagpur(印度理工学院卡拉格普尔分校);Indo-Korea Science and Technology(印韩科学技术院)

Souradip Guha, Ankan Mullick, Jatin Agrawal, Swetarekha Ram, Samir Ghui, Seung-Cheol Lee, Satadeep Bhattacharjee, Pawan Goyal

摘要:

材料科学领域发表的文章数量每年都在快速增长。这种相对非结构化的数据源包含大量信息,其可重用性受到限制,因为使用其中的数据进行进一步计算所需的信息必须手动提取。从在线(离线)数据中获得有效和上下文正确的信息非常重要,因为它不仅可以用于生成用于进一步计算的输入,而且还可以将其纳入查询框架。为了优先考虑这一背景,我们开发了一个自动化工具MatScIE(材料科学信息提取器),它可以从材料科学文献中提取相关信息,并建立一个更容易用于材料模拟的结构化数据库。具体来说,我们从各种研究文章中提取材料细节,方法,代码,参数和结构。最后,我们创建了一个Web应用程序,用户可以上传已发表的文章,查看/下载从该工具获得的信息,并可以创建自己的数据库供个人使用。

英文摘要:

The number of published articles in the field of materials science is growing rapidly every year. This comparatively unstructured data source, which contains a large amount of information, has a restriction on its re-usability, as the information needed to carry out further calculations using the data in it must be extracted manually. It is very important to obtain valid and contextually correct information from the online (offline) data, as it can be useful not only to generate inputs for further calculations, but also to incorporate them into a querying framework. Retaining this context as a priority, we have developed an automated tool, MatScIE (Material Scince Information Extractor) that can extract relevant information from material science literature and make a structured database that is much easier to use for material simulations. Specifically, we extract the material details, methods, code, parameters, and structure from the various research articles. Finally, we created a web application where users can upload published articles and view/download the information obtained from this tool and can create their own databases for their personal uses.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑