Named Entity Recognition and Normalization Applied to Large-Scale Information Extraction from the Materials Science Literature

By Leigh Weston, V. Tshitoyan, John Dagdelen, Olga Kononova, Amalie Trewartha, Kristin A. Persson, Gerbrand Ceder, Anubhav Jain. Journal of Chemical Information and Modeling, 2019

297 citations recorded by the source corpus.

The number of published materials science articles has increased manyfold over the past few decades. Now, a major bottleneck in the materials discovery pipeline arises in connecting new results with the previously established literature. A potential solution to this problem is to map the unstructured raw-text of published articles onto structured database entries that allows for programmatic querying. To this end, we apply text-mining with named entity recognition (NER) for large-scale information extraction from the published materials science literature. The NER model is trained to extract summary-level information from materials science documents, including: inorganic material mentions, sample descriptors, phase labels, material properties and applications, as well as any synthesis and characterization methods used. Our classifier achieves an accuracy (f1) of 87%, and is applied to information extraction from 3.27 million materials science abstracts. We extract more than 80 million materials-science-related named entities, and the content of each abstract is represented as a database entry in a structured format. We demonstrate that simple database queries can be used to answer complex ``meta-questions" of the published literature that would have previously required laborious, manual literature searches to answer. All of our data and functionality has been made freely available (https://github.com/materialsintelligence/matscholar), and we expect these results to accelerate the pace of future materials science discovery.

Subfields: Artificial Intelligence, Management Science and Operations Research, Materials Chemistry

View Paper: https://www.semanticscholar.org/paper/d2339ae1d60dfa90d24b54b3921c848e4ed8e889

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Daniel S. Weld
2. Kyle Lo
3. Lucy Lu Wang
4. Oren Etzioni
5. Mausam
6. Mohd Zaki
7. Tanishq Gupta
8. N. Krishnan

In Management Science and Operations Research

1. Oren Etzioni
2. Daniel S. Weld
3. John Dagdelen
4. Gerbrand Ceder
5. Lucy Lu Wang
6. Kyle Lo

In Materials Chemistry

1. Kuansan Wang
2. Gerbrand Ceder
3. Shyue Ping Ong
4. Axel van de Walle
5. Kristin A. Persson
6. Anubhav Jain

Citations in the corpus

• MatSciBERT: A materials domain language model for text mining and information extraction (2021, methodology): “Matscholar NER dataset9 by Weston et al. (2019): This dataset is publicly available and contains seven different entity types.”
• CORD-19: The Covid-19 Open Research Dataset (2020, methodology): “COVIDSCHOLAR20 is a COVID-19-specific adaptation of the MATSCHOLAR (Weston et al., 2019) system for identifying relevant papers given entitycentric queries.”
• Structured information extraction from scientific text with large language models (2024, methodology): “Similarly, zero-shot approaches without fi ne-tuning may make scienti fi c informationextractionmoreaccessibleattheexpenseofaccuracy(see Supplementary Discussion 6).”