Superconductivity information extraction from the literature: A new corpus and its evaluations. (October 2022)

• Record Type: Journal Article
• Authors: Yamaguchi, Kyosuke; Asahi, Ryoji; Sasaki, Yutaka
• Is Part Of: Advanced engineering informatics. Volume 54(2022)
• Publication Date: 2022-10
• Subjects: Materials informatics -- Information extraction -- Corpora -- Annotation -- Superconductivity; Computer-aided engineering -- Periodicals; Engineering -- Data processing -- Periodicals; 620.00285
• DOI: 10.1016/j.aei.2022.101768
• Languages: English
• ISSNs: 1474-0346

Abstract

Abstract: This paper describes a superconductivity corpus for materials informatics (SC-CoMIcs) tailored for the extraction of superconductive material information from the literature. Currently, few corpora exist for materials informatics in contrast to the situation for biomedical informatics. In particular, there is no sizable corpus that can be used to assist with the search for superconducting materials. The SC-CoMIcs consists of 1, 000 abstracts with manually annotated named entities, main materials, and relations/events associated with superconductivity. In particular, the main material is a selling point of our corpus, which can be regarded as a hub that binds implicitly related physical entities and properties in abstracts. We conduct named entity recognition, main material identification, and relation/event extraction experiments to determine the effectiveness of the corpus. The experimental results show that we can obtain F1 scores of approximately 74%–95%, 84% and 73%–97% for named entity recognition, main material identification and relation extraction tasks, respectively. We also demonstrate that the extracted doping information is consistent with that of the well-known Hume–Rothery rules, which implies that the constructed corpus can provide an opportunity to revisit or find physical chemical rules from the literature.