TeX 59%
Python 40.8%
1{"status": "ok", "message-type": "work", "message-version": "1.0.0", "message": {"indexed": {"date-parts": [[2026, 10, 18]], "date-time": "2026-10-18T01:33:38Z", "timestamp": 1792287218697, "version": "4.4.0"}, "reference-count": 67, "publisher": "Springer Science and Business Media LLC", "issue": "1", "license": [{"start": {"date-parts": [[2024, 2, 15]], "date-time": "2024-02-15T00:00:00Z", "timestamp": 1707955200000}, "content-version": "tdm", "delay-in-days": 0, "URL": "https://creativecommons.org/licenses/by/4.0"}, {"start": {"date-parts": [[2024, 2, 15]], "date-time": "2024-02-15T00:00:00Z", "timestamp": 1707955200000}, "content-version": "vor", "delay-in-days": 0, "URL": "https://creativecommons.org/licenses/by/4.0"}], "content-domain": {"domain": ["link.springer.com"], "crossmark-restriction": false}, "short-container-title": ["Nat Commun"], "abstract": "<jats:title>Abstract</jats:title>\n <jats:p>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.</jats:p>", "DOI": "10.1038/s41467-024-45563-x", "type": "journal-article", "created": {"date-parts": [[2024, 2, 15]], "date-time": "2024-02-15T15:02:29Z", "timestamp": 1708009349000}, "update-policy": "https://doi.org/10.1007/springer_crossmark_policy", "source": "Crossref", "is-referenced-by-count": 773, "title": ["Structured information extraction from scientific text with large language models"], "prefix": "10.1038", "volume": "15", "author": [{"ORCID": "https://orcid.org/0000-0003-2181-4815", "authenticated-orcid": false, "given": "John", "family": "Dagdelen", "sequence": "first", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"ORCID": "https://orcid.org/0000-0002-8567-1879", "authenticated-orcid": false, "given": "Alexander", "family": "Dunn", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Sanghoon", "family": "Lee", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Nicholas", "family": "Walker", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"ORCID": "https://orcid.org/0000-0002-0141-7006", "authenticated-orcid": false, "given": "Andrew S.", "family": "Rosen", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"given": "Gerbrand", "family": "Ceder", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"ORCID": "https://orcid.org/0000-0003-2495-5509", "authenticated-orcid": false, "given": "Kristin A.", "family": "Persson", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}, {"ORCID": "https://orcid.org/0000-0001-5893-9967", "authenticated-orcid": false, "given": "Anubhav", "family": "Jain", "sequence": "additional", "affiliation": [], "role": [{"vocabulary": "crossref", "role": "author"}]}], "member": "297", "published-online": {"date-parts": [[2024, 2, 15]]}, "reference": [{"key": "45563_CR1", "doi-asserted-by": "publisher", "first-page": "49", "DOI": "10.1146/annurev-matsci-090319-010954", "volume": "50", "author": "JE Saal", "year": "2020", "unstructured": "Saal, J. E., Oliynyk, A. O. & Meredig, B. Machine learning in materials discovery: confirmed predictions and their underlying approaches. Annu. Rev. Mater. Res. 50, 49–69 (2020).", "journal-title": "Annu. Rev. Mater. Res."}, {"key": "45563_CR2", "doi-asserted-by": "publisher", "DOI": "10.1038/s41524-022-00734-6", "volume": "8", "author": "K Choudhary", "year": "2022", "unstructured": "Choudhary, K. et al. Recent advances and applications of deep learning methods in materials science. npj Comput. Mater. 8, 59 (2022).", "journal-title": "npj Comput. Mater."}, {"key": "45563_CR3", "doi-asserted-by": "publisher", "first-page": "930369", "DOI": "10.3389/fchem.2022.930369", "volume": "10", "author": "ON Oliveira", "year": "2022", "unstructured": "Oliveira, O. N. & Oliveira, M. C. F. Materials discovery with machine learning and knowledge discovery. Front. Chem. 10, 930369 (2022).", "journal-title": "Front. Chem."}, {"key": "45563_CR4", "doi-asserted-by": "publisher", "first-page": "3692", "DOI": "10.1021/acs.jcim.9b00470", "volume": "59", "author": "L Weston", "year": "2019", "unstructured": "Weston, L. et al. Named entity recognition and normalization applied to large-scale information extraction from the materials science literature. J. Chem. Inform. Modeling 59, 3692–3702 (2019).", "journal-title": "J. Chem. Inform. Modeling"}, {"key": "45563_CR5", "doi-asserted-by": "publisher", "first-page": "100488", "DOI": "10.1016/j.patter.2022.100488", "volume": "3", "author": "A Trewartha", "year": "2022", "unstructured": "Trewartha, A. et al. Quantifying the advantage of domain-specific pre-training on named entity recognition tasks in materials science. Patterns 3, 100488 (2022).", "journal-title": "Patterns"}, {"key": "45563_CR6", "doi-asserted-by": "publisher", "first-page": "1207", "DOI": "10.1021/acs.jcim.1c01199", "volume": "62", "author": "T Isazawa", "year": "2022", "unstructured": "Isazawa, T. & Cole, J. M. Single model for organic and inorganic chemical named entity recognition in ChemDataExtractor. J. Chem. Inform. Modeling 62, 1207–1213 (2022).", "journal-title": "J. Chem. Inform. Modeling"}, {"key": "45563_CR7", "doi-asserted-by": "publisher", "unstructured": "Zhao, X., Greenberg, J., An, Y. & Hu, X. T. Fine-tuning BERT model for materials named entity recognition. In: 2021 IEEE International Conference on Big Data (Big Data) (IEEE, 2021). https://doi.org/10.1109/bigdata52589.2021.9671697.", "DOI": "10.1109/bigdata52589.2021.9671697"}, {"key": "45563_CR8", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-022-01752-1", "volume": "9", "author": "O Sierepeklis", "year": "2022", "unstructured": "Sierepeklis, O. & Cole, J. M. A thermoelectric materials database auto-generated from the scientific literature using chemdataextractor. Sci. data 9, 648 (2022).", "journal-title": "Sci. data"}, {"key": "45563_CR9", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-022-01355-w", "volume": "9", "author": "EJ Beard", "year": "2022", "unstructured": "Beard, E. J. & Cole, J. M. Perovskite- and dye-sensitized solar-cell device databases auto-generated using chemdataextractor. Sci. Data 9, 329 (2022).", "journal-title": "Sci. Data"}, {"key": "45563_CR10", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-022-01301-w", "volume": "9", "author": "P Kumar", "year": "2022", "unstructured": "Kumar, P., Kabra, S. & Cole, J. M. Auto-generating databases of yield strength and grain size using chemdataextractor. Sci. Data 9, 292 (2022).", "journal-title": "Sci. Data"}, {"key": "45563_CR11", "doi-asserted-by": "publisher", "first-page": "6365", "DOI": "10.1021/acs.jcim.2c00035", "volume": "62", "author": "S Huang", "year": "2022", "unstructured": "Huang, S. & Cole, J. M. BatteryBERT: A pretrained language model for battery database enhancement. J. Chem. Inform. Modeling 62, 6365–6377 (2022).", "journal-title": "J. Chem. Inform. Modeling"}, {"key": "45563_CR12", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-022-01294-6", "volume": "9", "author": "Q Dong", "year": "2022", "unstructured": "Dong, Q. & Cole, J. M. Auto-generated database of semiconductor band gaps using chemdataextractor. Sci. Data 9, 193 (2022).", "journal-title": "Sci. Data"}, {"key": "45563_CR13", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-019-0224-1", "volume": "6", "author": "O Kononova", "year": "2019", "unstructured": "Kononova, O. et al. Text-mined dataset of inorganic materials synthesis recipes. Sci. Data 6, 203 (2019).", "journal-title": "Sci. Data"}, {"key": "45563_CR14", "doi-asserted-by": "publisher", "first-page": "7323", "DOI": "10.1021/acs.chemmater.2c01293", "volume": "34", "author": "H Huo", "year": "2022", "unstructured": "Huo, H. et al. Machine-learning rationalization and prediction of solid-state synthesis conditions. Chem. Mater. 34, 7323–7336 (2022).", "journal-title": "Chem. Mater."}, {"key": "45563_CR15", "doi-asserted-by": "publisher", "first-page": "7861", "DOI": "10.1021/acs.chemmater.0c02553", "volume": "32", "author": "T He", "year": "2020", "unstructured": "He, T. et al. Similarity of precursors in solid-state synthesis as text-mined from scientific literature. Chem. of Mater. 32, 7861–7873 (2020).", "journal-title": "Chem. of Mater."}, {"key": "45563_CR16", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-022-01317-2", "volume": "9", "author": "Z Wang", "year": "2022", "unstructured": "Wang, Z. et al. Dataset of solution-based inorganic materials synthesis procedures extracted from the scientific literature. Sci. Data 9, 231 (2022).", "journal-title": "Sci. Data"}, {"key": "45563_CR17", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-020-00602-2", "volume": "7", "author": "S Huang", "year": "2020", "unstructured": "Huang, S. & Cole, J. M. A database of battery materials auto-generated using ChemDataExtractor. Sci. Data 7, 260 (2020).", "journal-title": "Sci. Data"}, {"key": "45563_CR18", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-019-0306-0", "volume": "6", "author": "EJ Beard", "year": "2019", "unstructured": "Beard, E. J., Sivaraman, G., Vázquez-Mayagoitia, Á., Vishwanath, V. & Cole, J. M. Comparative dataset of experimental and computational attributes of UV/vis absorption spectra. Sci. Data 6, 307 (2019).", "journal-title": "Sci. Data"}, {"key": "45563_CR19", "doi-asserted-by": "publisher", "DOI": "10.1038/s41597-022-01295-5", "volume": "9", "author": "J Zhao", "year": "2022", "unstructured": "Zhao, J. & Cole, J. M. A database of refractive indices and dielectric constants auto-generated using ChemDataExtractor. Sci. Data 9, 192 (2022).", "journal-title": "Sci. Data"}, {"key": "45563_CR20", "doi-asserted-by": "publisher", "first-page": "34", "DOI": "10.1016/j.eswa.2018.07.032", "volume": "114", "author": "G Bekoulis", "year": "2018", "unstructured": "Bekoulis, G., Deleu, J., Demeester, T. & Develder, C. Joint entity recognition and relation extraction as a multi-head selection problem. Expert Syst. Appl. 114, 34–45 (2018).", "journal-title": "Expert Syst. Appl."}, {"key": "45563_CR21", "unstructured": "Han, X. et al. More data, more relations, more context and more openness: a review and outlook for relation extraction. In: Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, 745–758. (Association for Computational Linguistics, 2020). https://aclanthology.org/2020.aacl-main.75."}, {"key": "45563_CR22", "doi-asserted-by": "crossref", "unstructured": "Yao, Y. et al. DocRED: A large-scale document-level relation extraction dataset. In: Proc. 57th Annual Meeting of the Association for Computational Linguistics, 764–777 (Association for Computational Linguistics, 2019). https://aclanthology.org/P19-1074.", "DOI": "10.18653/v1/P19-1074"}, {"key": "45563_CR23", "doi-asserted-by": "crossref", "unstructured": "Li, J. et al. Biocreative v cdr task corpus: a resource for chemical disease relation extraction. Database 2016 (2016).", "DOI": "10.1093/database/baw068"}, {"key": "45563_CR24", "doi-asserted-by": "publisher", "first-page": "1", "DOI": "10.1186/s12859-015-0472-9", "volume": "16", "author": "Á Bravo", "year": "2015", "unstructured": "Bravo, Á., Piñero, J., Queralt-Rosinach, N., Rautschka, M. & Furlong, L. I. Extraction of relations between genes and diseases from text and large-scale data analysis: Implications for translational research. BMC Bioinformatics 16, 1–17 (2015).", "journal-title": "BMC Bioinformatics"}, {"key": "45563_CR25", "doi-asserted-by": "crossref", "unstructured": "Yang, X. et al. Pcmsp: A dataset for scientific action graphs extraction from polycrystalline materials synthesis procedure text. In: Findings of the Association for Computational Linguistics: EMNLP 2022, 6033–6046 (Association for Computational Linguistics, 2022). https://aclanthology.org/2022.findings-emnlp.446.", "DOI": "10.18653/v1/2022.findings-emnlp.446"}, {"key": "45563_CR26", "unstructured": "Brown, T. B. et al. Language models are few-shot learners. Preprint at https://browse.arxiv.org/abs/2005.14165 (2020)."}, {"key": "45563_CR27", "unstructured": "OpenAI. Gpt-4 technical report. Preprint at https://browse.arxiv.org/abs/2303.08774 (2023)."}, {"key": "45563_CR28", "unstructured": "Chowdhery, A. et al. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 1–113 (2023)."}, {"key": "45563_CR29", "unstructured": "Smith, S. et al. Using deepspeed and megatron to train megatron-turing nlg 530b, a large-scale generative language model. Preprint at https://arxiv.org/abs/2201.11990 (2022)."}, {"key": "45563_CR30", "unstructured": "Touvron, H. et al. Llama: Open and efficient foundation language models. Preprint at https://arxiv.org/abs/2302.13971 (2023)."}, {"key": "45563_CR31", "unstructured": "Touvron, H. et al. Llama 2: Open foundation and fine-tuned chat models. Preprint at https://arxiv.org/abs/2307.09288 (2023)."}, {"key": "45563_CR32", "unstructured": "Zhang, S. et al. Opt: Open pre-trained transformer language models. Preprint at https://browse.arxiv.org/abs/2205.01068 (2022)."}, {"key": "45563_CR33", "unstructured": "Hoffmann, J. et al. Training compute-optimal large language models. Preprint at http://arxiv.org/abs/2203.15556 (2022)."}, {"key": "45563_CR34", "unstructured": "Wei, J. et al. Finetuned language models are zero-shot learners. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=gEZrGCozdqR."}, {"key": "45563_CR35", "unstructured": "BIG-bench collaboration. Beyond the imitation game: measuring and extrapolating the capabilities of language models. In preparation. https://github.com/google/BIG-bench/ (2021)."}, {"key": "45563_CR36", "doi-asserted-by": "publisher", "first-page": "1", "DOI": "10.1145/3406095", "volume": "53", "author": "R Dabre", "year": "2020", "unstructured": "Dabre, R., Chu, C. & Kunchukuttan, A. A survey of multilingual neural machine translation. ACM Comput. Surv. 53, 1–38 (2020).", "journal-title": "ACM Comput. Surv."}, {"key": "45563_CR37", "doi-asserted-by": "crossref", "unstructured": "Petroni, F. et al. Language models as knowledge bases? In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2463–2473 (Association for Computational Linguistics, 2019). https://aclanthology.org/D19-1250.", "DOI": "10.18653/v1/D19-1250"}, {"key": "45563_CR38", "unstructured": "Han, J. M. et al. Unsupervised neural machine translation with generative language models only. https://openreview.net/forum?id=SVwbKmEg7M (2022)."}, {"key": "45563_CR39", "doi-asserted-by": "crossref", "unstructured": "Zhang, H., Xu, J. & Wang, J. Pretraining-based natural language generation for text summarization. In: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), 789–797 (Association for Computational Linguistics, 2019). https://aclanthology.org/K19-1074.", "DOI": "10.18653/v1/K19-1074"}, {"key": "45563_CR40", "doi-asserted-by": "crossref", "unstructured": "Liu, Z. et al. Multi-stage prompting for knowledgeable dialogue generation. In: Findings of the Association for Computational Linguistics: ACL 2022, 1317–1337 (Association for Computational Linguistics, 2022). https://aclanthology.org/2022.findings-acl.104.", "DOI": "10.18653/v1/2022.findings-acl.104"}, {"key": "45563_CR41", "doi-asserted-by": "crossref", "unstructured": "Giorgi, J., Bader, G. & Wang, B. A sequence-to-sequence approach for document-level relation extraction. In: Proc. 21st Workshop on Biomedical Language Processing, 10–25 (Association for Computational Linguistics, 2022). https://aclanthology.org/2022.bionlp-1.2.", "DOI": "10.18653/v1/2022.bionlp-1.2"}, {"key": "45563_CR42", "doi-asserted-by": "publisher", "unstructured": "Cabot, P.-L. H. & Navigli, R. REBEL: Relation extraction by end-to-end language generation. In: Findings of the Association for Computational Linguistics: EMNLP 2021 (Association for Computational Linguistics, 2021). https://doi.org/10.18653/v1/2021.findings-emnlp.204.", "DOI": "10.18653/v1/2021.findings-emnlp.204"}, {"key": "45563_CR43", "unstructured": "Townsend, B., Ito-Fisher, E., Zhang, L. & May, M. Doc2dict: Information extraction as text generation. Preprint at http://arxiv.org/abs/2105.07510 (2021)."}, {"key": "45563_CR44", "doi-asserted-by": "publisher", "first-page": "18048", "DOI": "10.1021/jacs.3c05819", "volume": "145", "author": "Z Zheng", "year": "2023", "unstructured": "Zheng, Z., Zhang, O., Borgs, C., Chayes, J. T. & Yaghi, O. M. ChatGPT chemistry assistant for text mining and the prediction of MOF synthesis. J. Am. Chem. Soc. 145, 18048–18062 (2023).", "journal-title": "J. Am. Chem. Soc."}, {"key": "45563_CR45", "unstructured": "OpenAI et al. Introducing chatgpt https://openai.com/blog/chatgpt (2022)."}, {"key": "45563_CR46", "doi-asserted-by": "publisher", "first-page": "1649", "DOI": "10.1021/acs.jcim.3c00285", "volume": "63", "author": "CM Castro Nascimento", "year": "2023", "unstructured": "Castro Nascimento, C. M. & Pimentel, A. S. Do large language models understand chemistry? a conversation with chatgpt. J. Chem. Inform. Modeling 63, 1649–1655 (2023).", "journal-title": "J. Chem. Inform. Modeling"}, {"key": "45563_CR47", "doi-asserted-by": "publisher", "first-page": "368", "DOI": "10.1039/D2DD00087C", "volume": "2", "author": "AD White", "year": "2023", "unstructured": "White, A. D. et al. Assessment of chemistry knowledge in large language models that generate code. Digital Discov. 2, 368–376 (2023).", "journal-title": "Digital Discov."}, {"key": "45563_CR48", "unstructured": "Xie, T. et al. Darwin series: Domain specific large language models for natural science. Preprint at https://arxiv.org/abs/2308.13565 (2023)."}, {"key": "45563_CR49", "doi-asserted-by": "publisher", "unstructured": "Jablonka, K. M., Schwaller, P., Ortega-Guerrero, A. & Smit, B. Is GPT all you need for low-data discovery in chemistry? https://doi.org/10.26434/chemrxiv-2023-fw8n4-v2 (2023).", "DOI": "10.26434/chemrxiv-2023-fw8n4-v2"}, {"key": "45563_CR50", "doi-asserted-by": "crossref", "unstructured": "Jablonka, K. M. et al. 14 examples of how llms can transform materials science and chemistry: a reflection on a large language model hackathon. Digital Discov. 2, 1233–1250 (2023).", "DOI": "10.1039/D3DD00113J"}, {"key": "45563_CR51", "doi-asserted-by": "crossref", "unstructured": "Gu, Y. et al. Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthcare 3, 1 (2021).", "DOI": "10.1145/3458754"}, {"key": "45563_CR52", "doi-asserted-by": "crossref", "unstructured": "Mosqueira-Rey, E., Hernández-Pereira, E., Alonso-Ríos, D., Bobes-Bascarán, J. & Fernández-Leal, Á. Human-in-the-loop machine learning: a state of the art. Artif. Intel. Rev. 56, 1–50 (2022).", "DOI": "10.1007/s10462-022-10246-w"}, {"key": "45563_CR53", "doi-asserted-by": "publisher", "unstructured": "Maynez, J., Narayan, S., Bohnet, B. & McDonald, R. On faithfulness and factuality in abstractive summarization. In: Proc. 58th Annual Meeting of the Association for Computational Linguistics (Association for Computational Linguistics, 2020). https://doi.org/10.18653/v1/2020.acl-main.173.", "DOI": "10.18653/v1/2020.acl-main"}, {"key": "45563_CR54", "doi-asserted-by": "crossref", "unstructured": "Ji, Z. et al. Survey of hallucination in natural language generation. ACM Comput. Surv. 55, 12 (2023).", "DOI": "10.1145/3571730"}, {"key": "45563_CR55", "doi-asserted-by": "crossref", "unstructured": "Black, S. et al. Gpt-neox-20b: An open-source autoregressive language model. Preprint at https://browse.arxiv.org/abs/2204.06745 (2022).", "DOI": "10.18653/v1/2022.bigscience-1.9"}, {"key": "45563_CR56", "unstructured": "Frantar, E. & Alistarh, D. Sparsegpt: Massive language models can be accurately pruned in one-shot. In: Proceedings of the 40th International Conference on Machine Learning, 10323–10337 (JLMR.org, 2023). https://proceedings.mlr.press/v202/frantar23a/frantar23a.pdf."}, {"key": "45563_CR57", "unstructured": "Sun, M., Liu, Z., Bair, A. & Kolter, J. Z. A simple and effective pruning approach for large language models. In: Workshop on Efficient Systems for Foundation Models @ ICML2023. https://openreview.net/forum?id=tz9JV2PRSv (2023)."}, {"key": "45563_CR58", "unstructured": "Hu, E. J. et al. Lora: Low-rank adaptation of large language models. Preprint at https://arxiv.org/abs/2106.09685 (2021)."}, {"key": "45563_CR59", "unstructured": "Ma, X., Fang, G. & Wang, X. Llm-pruner: On the structural pruning of large language models. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https://openreview.net/forum?id=J8Ajf9WfXP."}, {"key": "45563_CR60", "doi-asserted-by": "publisher", "first-page": "6682", "DOI": "10.1021/acs.cgd.9b01050", "volume": "19", "author": "BJ Bucior", "year": "2019", "unstructured": "Bucior, B. J. et al. Identification schemes for metal–organic frameworks to enable rapid search and cheminformatics analysis. Cryst. Growth Des. 19, 6682–6697 (2019).", "journal-title": "Cryst. Growth Des."}, {"key": "45563_CR61", "doi-asserted-by": "publisher", "first-page": "2000790", "DOI": "10.1002/admt.202000790", "volume": "6", "author": "X Li", "year": "2021", "unstructured": "Li, X., Hill, M. R., Wang, H. & Zhang, H. Metal–organic framework-based ion-selective membranes. Adv. Mater. Technol. 6, 2000790 (2021).", "journal-title": "Adv. Mater. Technol."}, {"key": "45563_CR62", "doi-asserted-by": "publisher", "first-page": "8161", "DOI": "10.1021/acs.chemrev.0c00119", "volume": "120", "author": "Q Qian", "year": "2020", "unstructured": "Qian, Q. et al. Mof-based membranes for gas separations. Chem. Rev. 120, 8161–8266 (2020).", "journal-title": "Chem. Rev."}, {"key": "45563_CR63", "doi-asserted-by": "publisher", "first-page": "95", "DOI": "10.1038/s41586-019-1335-8", "volume": "571", "author": "V Tshitoyan", "year": "2019", "unstructured": "Tshitoyan, V. et al. Unsupervised word embeddings capture latent knowledge from materials science literature. Nature 571, 95–98 (2019).", "journal-title": "Nature"}, {"key": "45563_CR64", "unstructured": "Kluyver, T. et al. Jupyter notebooks—a publishing format for reproducible computational workflows. In: Positioning and Power in Academic Publishing: Players, Agents and Agendas (eds. Loizides, F. & Schmidt, B.) 87–90 (IOS Press, 2016)."}, {"key": "45563_CR65", "doi-asserted-by": "publisher", "unstructured": "Dagdelen, J. et al. Structured information extraction from scientific text with large language models https://doi.org/10.5281/zenodo.10421174 (2023).", "DOI": "10.5281/zenodo.10421174"}, {"key": "45563_CR66", "doi-asserted-by": "publisher", "unstructured": "Dagdelen, J. et al. Llama 2 code for structured information extraction from scientific text with large language models. https://doi.org/10.5281/zenodo.10421187 (2023).", "DOI": "10.5281/zenodo.10421187"}, {"key": "45563_CR67", "doi-asserted-by": "publisher", "unstructured": "Dagdelen, J. et al. Llama 2 weights for structured information extraction from scientific text with large language models. https://doi.org/10.6084/m9.figshare.24501331.v1 (2023).", "DOI": "10.6084/m9.figshare.24501331.v1"}], "container-title": ["Nature Communications"], "original-title": [], "language": "en", "link": [{"URL": "https://www.nature.com/articles/s41467-024-45563-x.pdf", "content-type": "application/pdf", "content-version": "vor", "intended-application": "text-mining"}, {"URL": "https://www.nature.com/articles/s41467-024-45563-x", "content-type": "text/html", "content-version": "vor", "intended-application": "text-mining"}, {"URL": "https://www.nature.com/articles/s41467-024-45563-x.pdf", "content-type": "application/pdf", "content-version": "vor", "intended-application": "similarity-checking"}], "deposited": {"date-parts": [[2024, 2, 18]], "date-time": "2024-02-18T19:08:24Z", "timestamp": 1708283304000}, "score": 1, "resource": {"primary": {"URL": "https://www.nature.com/articles/s41467-024-45563-x"}}, "subtitle": [], "short-title": [], "issued": {"date-parts": [[2024, 2, 15]]}, "references-count": 67, "journal-issue": {"issue": "1", "published-online": {"date-parts": [[2024, 12]]}}, "alternative-id": ["45563"], "URL": "https://doi.org/10.1038/s41467-024-45563-x", "relation": {}, "ISSN": ["2041-1723"], "issn-type": [{"value": "2041-1723", "type": "electronic"}], "subject": [], "published": {"date-parts": [[2024, 2, 15]]}, "assertion": [{"value": "17 March 2023", "order": 1, "name": "received", "label": "Received", "group": {"name": "ArticleHistory", "label": "Article History"}}, {"value": "22 January 2024", "order": 2, "name": "accepted", "label": "Accepted", "group": {"name": "ArticleHistory", "label": "Article History"}}, {"value": "15 February 2024", "order": 3, "name": "first_online", "label": "First Online", "group": {"name": "ArticleHistory", "label": "Article History"}}, {"value": "The authors declare no competing interests.", "order": 1, "name": "Ethics", "group": {"name": "EthicsHeading", "label": "Competing interests"}}], "article-number": "1418"}}