MatSciBERT: A materials domain language model for text mining and information extraction

Abstract A large amount of materials science knowledge is generated and stored as text published in peer-reviewed scientific literature. While recent developments in natural language processing, such as Bidirectional Encoder Representations from Transformers (BERT) models, provide promising information extraction tools, these models may yield suboptimal results when applied on materials domain since they are not trained in materials science specific notations and jargons. Here, we present a materials-aware language model, namely, MatSciBERT, trained on a large corpus of peer-reviewed materials science publications. We show that MatSciBERT outperforms SciBERT, a language model trained on science corpus, and…

• IB
  International Business Machines Corporation
• BL
  Bloomberg L.P.
• G
  Google
• DO
  Department of Science and Technology, Ministry of Science and Technology, India

  Awards: ECR/2018/002228, DST/INSPIRE/04/2016/002774
• IS
  Indian Space Research Organisation
• MO
  Ministry of Education, India
• II
  Indian Institute of Technology Delhi
• SA
  Science and Engineering Research Board

  Award: ECR/2018/002228
• BO
  Board of Research in Nuclear Sciences

  Award: 53/20/01/2021-BRNS