%0 Journal Article %1 Dagdelen2024 %A Dagdelen, John %A Dunn, Alexander %A Lee, Sanghoon %A Walker, Nicholas %A Rosen, Andrew S. %A Ceder, Gerbrand %A Persson, Kristin A. %A Jain, Anubhav %D 2024 %J Nature Communications %K extraction llm %N 1 %P 1418 %R 10.1038/s41467-024-45563-x %T Structured information extraction from scientific text with large language models %U https://doi.org/10.1038/s41467-024-45563-x %V 15 %X 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.

@article{Dagdelen2024, 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.}, added-at = {2024-03-12T14:45:28.000+0100}, author = {Dagdelen, John and Dunn, Alexander and Lee, Sanghoon and Walker, Nicholas and Rosen, Andrew S. and Ceder, Gerbrand and Persson, Kristin A. and Jain, Anubhav}, biburl = {https://www.bibsonomy.org/bibtex/2225a58ffb93eeb3a6761fac24c50ce69/mho}, day = 15, description = {Structured information extraction from scientific text with large language models | Nature Communications}, doi = {10.1038/s41467-024-45563-x}, interhash = {de2f26a3b10f362ac45d9414b59c0304}, intrahash = {225a58ffb93eeb3a6761fac24c50ce69}, issn = {2041-1723}, journal = {Nature Communications}, keywords = {extraction llm}, month = feb, number = 1, pages = 1418, timestamp = {2024-03-12T14:45:28.000+0100}, title = {Structured information extraction from scientific text with large language models}, url = {https://doi.org/10.1038/s41467-024-45563-x}, volume = 15, year = 2024 }