Annotating and Extracting Synthesis Process of All-Solid-State Batteries from Scientific Literature

Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 1941–1950 Marseille, 11–16 May 2020 c⃝ European Language Resources Association (ELRA), licensed under CC-BY-NC 1941 Annotating and Extracting Synthesis Process of All-Solid-State Batteries from Scientific Literature Fusataka Kuniyoshi1,3, Kohei Makino2,3, Jun Ozawa1,3, Makoto Miwa2,3 1Panasonic Corporation 2Toyota Technological Institute 3National Institute of Advanced Industrial Science and Technology (AIST) {kuniyoshi.fusataka, kohei.makino, ozawa.jun, makoto.miwa}@aist.go.jp Abstract The synthesis process is essential for achieving computational experiment design in the field of inorganic materials chemistry. In this work, we present a novel corpus of the synthesis process for all-solid-state batteries and an automated machine reading system for extracting the synthesis processes buried in the scientific literature. We define the representation of the synthesis processes using flow graphs, and create a corpus from the experimental sections of 243 papers. The automated machine-reading system is developed by a deep learning-based sequence tagger and simple heuristic rule-based relation extractor. Our experimental results demonstrate that the sequence tagger with the optimal setting can detect the entities with a macro-averaged F1 score of 0.826, while the rule-based relation extractor can achieve high performance with a macro-averaged F1 score of 0.887. Keywords: Synthesis process, Flow graph, Corpus annotation, Named entity recognition, Relation extraction 1. Introduction With the rapid progress in the field of inorganic materials, such as the development of all-solid-state batteries (ASSBs) and solar cells, several materials researchers have noted the importance of reducing the overall discovery and de- velopment time by means of computational experiment de- sign, using the knowledge of published scientific litera- ture (Agrawal and Choudhary, 2016; Butler et al., 2018; Wei et al., 2019). To achieve this, automated machine read- ing systems that can comprehensively investigate the syn- thesis process buried in the scientific literature is necessary. In the field of organic chemistry, Krallinger et al. (2015) proposed a corpus in which chemical substances, drug names, and their relations are structurally annotated in doc- uments such as papers, patents, and medical documents, while composition names are provided in the abstracts of molecular biology papers. Linguistic resources are avail- able in abundance, such as the GENIA corpus (Kim et al., 2003) of biomedical events on biomedical texts and the an- notated corpus (Kulkarni et al., 2018) of liquid-phase ex- perimental processes on biological papers. In biomedical text mining, the detection of semantic relations is actively researched as a central task (Miwa et al., 2012; Scaria et al., 2013; Berant et al., 2014; Rao et al., 2017; Rahul et al., 2017; Bj¨orne and Salakoski, 2018). However, the relations in biomedical text mining represent the cause and effect of a physical phenomenon among two or more biochemical reactions, which differs from the procedure of synthesizing materials. In the field of inorganic chemistry, only several corpora have been proposed in recent years. Kononova et al. (2019) constructed a general-purpose corpus of material synthesis for inorganic material by aligning the phrases extracted by a trained sequence-tagging model. However, this corpus did not include relations between operations, and therefore, …

Content truncated to 500 words