arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.13136cs.CLcond-mat.mtrl-scicond-mat.soft
收藏

使用自然语言处理从大型聚合物语料库中提取通用材料属性数据的流水线

A general-purpose material property data extraction pipeline from large polymer corpora using Natural Language Processing

Georgia Institute of Technology(佐治亚理工学院)

Pranav Shetty, Arunkumar Chitteth Rajan, Christopher Kuenneth, Sonkakshi Gupta, Lakshmi Prerana Panchumarti, Lauren Holm, Chao Zhang, Rampi Ramprasad

AI总结:

本研究提出一种基于自然语言处理的自动流水线,利用MaterialsBERT模型从聚合物文献摘要中提取材料属性数据,在60小时内获取约30万条记录,并通过网络平台公开数据,验证了自动化提取的可行性。

摘要:

材料科学文章数量的不断增加,使得从已发表文献中推断化学-结构-属性关系变得困难。我们使用自然语言处理(NLP)方法从聚合物文献的摘要中自动提取材料属性数据。作为流水线的一个组件,我们使用240万篇材料科学摘要训练了MaterialsBERT这一语言模型,当其作为文本编码器时,在五个命名实体识别数据集中的三个数据集上优于其他基线模型。使用该流水线,我们在60小时内从约130,000篇摘要中获得了约300,000条材料属性记录。对提取的数据进行了多种应用分析,如燃料电池、超级电容器和聚合物太阳能电池,以恢复非平凡的见解。通过我们的流水线提取的数据可通过https://polymerscholar.org上的网络平台获取,该平台可用于方便地定位记录在摘要中的材料属性数据。这项工作证明了从已发表文献开始到最终获得完整提取的材料属性信息的自动流水线的可行性。

英文摘要:

The ever-increasing number of materials science articles makes it hard to infer chemistry-structure-property relations from published literature. We used natural language processing (NLP) methods to automatically extract material property data from the abstracts of polymer literature. As a component of our pipeline, we trained MaterialsBERT, a language model, using 2.4 million materials science abstracts, which outperforms other baseline models in three out of five named entity recognition datasets when used as the encoder for text. Using this pipeline, we obtained ~300,000 material property records from ~130,000 abstracts in 60 hours. The extracted data was analyzed for a diverse range of applications such as fuel cells, supercapacitors, and polymer solar cells to recover non-trivial insights. The data extracted through our pipeline is made available through a web platform at https://polymerscholar.org which can be used to locate material property data recorded in abstracts conveniently. This work demonstrates the feasibility of an automatic pipeline that starts from published literature and ends with a complete set of extracted material property information.

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。

↑