IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v15y2024i1d10.1038_s41467-024-45563-x.html
   My bibliography  Save this article

Structured information extraction from scientific text with large language models

Author

Listed:
  • John Dagdelen

    (Lawrence Berkeley National Laboratory
    University of California)

  • Alexander Dunn

    (Lawrence Berkeley National Laboratory
    University of California)

  • Sanghoon Lee

    (Lawrence Berkeley National Laboratory
    University of California)

  • Nicholas Walker

    (Lawrence Berkeley National Laboratory)

  • Andrew S. Rosen

    (Lawrence Berkeley National Laboratory
    University of California)

  • Gerbrand Ceder

    (Lawrence Berkeley National Laboratory
    University of California)

  • Kristin A. Persson

    (Lawrence Berkeley National Laboratory
    University of California)

  • Anubhav Jain

    (Lawrence Berkeley National Laboratory)

Abstract

Extracting structured knowledge from scientific text remains a challenging task for machine learning models. Here, we present a simple approach to joint named entity recognition and relation extraction and demonstrate how pretrained large language models (GPT-3, Llama-2) can be fine-tuned to extract useful records of complex scientific knowledge. We test three representative tasks in materials chemistry: linking dopants and host materials, cataloging metal-organic frameworks, and general composition/phase/morphology/application information extraction. Records are extracted from single sentences or entire paragraphs, and the output can be returned as simple English sentences or a more structured format such as a list of JSON objects. This approach represents a simple, accessible, and highly flexible route to obtaining large databases of structured specialized scientific knowledge extracted from research papers.

Suggested Citation

  • John Dagdelen & Alexander Dunn & Sanghoon Lee & Nicholas Walker & Andrew S. Rosen & Gerbrand Ceder & Kristin A. Persson & Anubhav Jain, 2024. "Structured information extraction from scientific text with large language models," Nature Communications, Nature, vol. 15(1), pages 1-14, December.
    • Handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-45563-x
    DOI: 10.1038/s41467-024-45563-x
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-024-45563-x
    File Function: Abstract
    Download Restriction: no
    File URL: https://libkey.io/10.1038/s41467-024-45563-x?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Vahe Tshitoyan & John Dagdelen & Leigh Weston & Alexander Dunn & Ziqin Rong & Olga Kononova & Kristin A. Persson & Gerbrand Ceder & Anubhav Jain, 2019. "Unsupervised word embeddings capture latent knowledge from materials science literature," Nature, Nature, vol. 571(7763), pages 95-98, July.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Ananthan Nambiar & Tobias Rubel & James McCaull & Jon deVries & Mark Bedau, 2021. "Dropping diversity of products of large US firms: Models and measures," Papers 2110.08367, arXiv.org.
    2. Jason Youn & Navneet Rai & Ilias Tagkopoulos, 2022. "Knowledge integration and decision support for accelerated discovery of antibiotic resistance genes," Nature Communications, Nature, vol. 13(1), pages 1-11, December.
    3. Zongrui Pei & Junqi Yin & Peter K. Liaw & Dierk Raabe, 2023. "Toward the design of ultrahigh-entropy alloys via mining six million texts," Nature Communications, Nature, vol. 14(1), pages 1-8, December.
    4. Shaoshuo Li & Baixing Chen & Hao Chen & Zhen Hua & Yang Shao & Heng Yin & Jianwei Wang, 2021. "Analysis of potential genetic biomarkers and molecular mechanism of smoking-related postmenopausal osteoporosis using weighted gene co-expression network analysis and machine learning," PLOS ONE, Public Library of Science, vol. 16(9), pages 1-18, September.
    5. Jianhong Luo & Minjuan Chai & Xuwei Pan, 2021. "Identification of Research Priorities during the COVID-19 Pandemic: Implications for Its Management," IJERPH, MDPI, vol. 18(24), pages 1-15, December.
    6. Aman Kumar & Binil Starly, 2022. "“FabNER”: information extraction from manufacturing process science domain literature using named entity recognition," Journal of Intelligent Manufacturing, Springer, vol. 33(8), pages 2393-2407, December.
    7. Sotaro Shibayama & Deyun Yin & Kuniko Matsumoto, 2021. "Measuring novelty in science with word embedding," PLOS ONE, Public Library of Science, vol. 16(7), pages 1-16, July.
    8. Pessa, Arthur A.B. & Zola, Rafael S. & Perc, Matjaž & Ribeiro, Haroldo V., 2022. "Determining liquid crystal properties with ordinal networks and machine learning," Chaos, Solitons & Fractals, Elsevier, vol. 154(C).
    9. Yonghe Lu & Jiayi Luo & Ying Xiao & Hou Zhu, 2021. "Text representation model of scientific papers based on fusing multi-viewpoint information and its quality assessment," Scientometrics, Springer;Akadémiai Kiadó, vol. 126(8), pages 6937-6963, August.
    10. Jiang, Zhuoren & Lin, Tianqianjin & Huang, Cui, 2023. "Deep representation learning of scientific paper reveals its potential scholarly impact," Journal of Informetrics, Elsevier, vol. 17(1).
    11. Lu Liu & Benjamin F. Jones & Brian Uzzi & Dashun Wang, 2023. "Data, measurement and empirical methods in the science of science," Nature Human Behaviour, Nature, vol. 7(7), pages 1046-1058, July.
    12. Shufeng Kong & Francesco Ricci & Dan Guevarra & Jeffrey B. Neaton & Carla P. Gomes & John M. Gregoire, 2022. "Density of states prediction for materials discovery via contrastive learning from probabilistic embeddings," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    13. Wu, Lingfei & Kittur, Aniket & Youn, Hyejin & Milojević, Staša & Leahey, Erin & Fiore, Stephen M. & Ahn, Yong-Yeol, 2022. "Metrics and mechanisms: Measuring the unmeasurable in the science of science," Journal of Informetrics, Elsevier, vol. 16(2).
    14. Gordana Ispirova & Tome Eftimov & Barbara Koroušić Seljak, 2020. "P-NUT: Predicting NUTrient Content from Short Text Descriptions," Mathematics, MDPI, vol. 8(10), pages 1-21, October.
    15. Lin, Yiling & Evans, James A. & Wu, Lingfei, 2022. "New directions in science emerge from disconnection and discord," Journal of Informetrics, Elsevier, vol. 16(1).
    16. Jeong, Yoo Kyung & Xie, Qing & Yan, Erjia & Song, Min, 2020. "Examining drug and side effect relation using author–entity pair bipartite networks," Journal of Informetrics, Elsevier, vol. 14(1).
    17. Jarrahi, Mohammad Hossein & Askay, David & Eshraghi, Ali & Smith, Preston, 2023. "Artificial intelligence and knowledge management: A partnership between human and AI," Business Horizons, Elsevier, vol. 66(1), pages 87-99.
    18. Martín de Diego, Isaac & González-Fernández, César & Fernández-Isabel, Alberto & Fernández, Rubén R. & Cabezas, Javier, 2021. "System for evaluating the reliability and novelty of medical scientific papers," Journal of Informetrics, Elsevier, vol. 15(4).
    19. Hain, Daniel S. & Jurowetzki, Roman & Buchmann, Tobias & Wolf, Patrick, 2022. "A text-embedding-based approach to measuring patent-to-patent technological similarity," Technological Forecasting and Social Change, Elsevier, vol. 177(C).
    20. Zachary A Pardos & Andrew Joo Hun Nam, 2020. "A university map of course knowledge," PLOS ONE, Public Library of Science, vol. 15(9), pages 1-24, September.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-45563-x. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.