{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:09:01Z","timestamp":1776352141056,"version":"3.51.2"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"7763","license":[{"start":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T00:00:00Z","timestamp":1562112000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T00:00:00Z","timestamp":1562112000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nature"],"published-print":{"date-parts":[[2019,7,4]]},"DOI":"10.1038\/s41586-019-1335-8","type":"journal-article","created":{"date-parts":[[2019,7,3]],"date-time":"2019-07-03T18:11:28Z","timestamp":1562177488000},"page":"95-98","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":908,"title":["Unsupervised word embeddings capture latent knowledge from materials science literature"],"prefix":"10.1038","volume":"571","author":[{"given":"Vahe","family":"Tshitoyan","sequence":"first","affiliation":[]},{"given":"John","family":"Dagdelen","sequence":"additional","affiliation":[]},{"given":"Leigh","family":"Weston","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Dunn","sequence":"additional","affiliation":[]},{"given":"Ziqin","family":"Rong","sequence":"additional","affiliation":[]},{"given":"Olga","family":"Kononova","sequence":"additional","affiliation":[]},{"given":"Kristin A.","family":"Persson","sequence":"additional","affiliation":[]},{"given":"Gerbrand","family":"Ceder","sequence":"additional","affiliation":[]},{"given":"Anubhav","family":"Jain","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,7,3]]},"reference":[{"key":"1335_CR1","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1557\/mrs.2016.93","volume":"41","author":"J Hill","year":"2016","unstructured":"Hill, J. et al. Materials science with large-scale data and informatics: unlocking new opportunities. MRS Bull. 41, 399\u2013409 (2016).","journal-title":"MRS Bull."},{"key":"1335_CR2","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","volume":"559","author":"KT Butler","year":"2018","unstructured":"Butler, K. T., Davies, D. W., Cartwright, H., Isayev, O. & Walsh, A. Machine learning for molecular and materials science. Nature 559, 547\u2013555 (2018).","journal-title":"Nature"},{"key":"1335_CR3","doi-asserted-by":"publisher","first-page":"S74","DOI":"10.1093\/bioinformatics\/17.suppl_1.S74","volume":"17","author":"C Friedman","year":"2001","unstructured":"Friedman, C., Kra, P., Yu, H., Krauthammer, M. & Rzhetsky, A. GENIES: a natural-language processing system for the extraction of molecular pathways from journal articles. Bioinformatics 17, S74\u2013S82 (2001).","journal-title":"Bioinformatics"},{"key":"1335_CR4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0020309","volume":"2","author":"HM M\u00fcller","year":"2004","unstructured":"M\u00fcller, H. M., Kenny, E. E. & Sternberg, P. W. Textpresso: an ontology-based information retrieval and extraction system for biological literature. PLoS Biol. 2, e309 (2004).","journal-title":"PLoS Biol."},{"key":"1335_CR5","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1021\/acs.jcim.6b00207","volume":"56","author":"MC Swain","year":"2016","unstructured":"Swain, M. C. & Cole, J. M. ChemDataExtractor: a toolkit for automated extraction of chemical information from the scientific literature. J. Chem. Inf. Model. 56, 1894\u20131904 (2016).","journal-title":"J. Chem. Inf. Model."},{"key":"1335_CR6","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/1758-2946-6-17","volume":"6","author":"S Eltyeb","year":"2014","unstructured":"Eltyeb, S. & Salim, N. Chemical named entities recognition: a review on approaches and applications. J. Cheminform. 6, 17 (2014).","journal-title":"J. Cheminform."},{"key":"1335_CR7","doi-asserted-by":"publisher","first-page":"9436","DOI":"10.1021\/acs.chemmater.7b03500","volume":"29","author":"E Kim","year":"2017","unstructured":"Kim, E. et al. Materials synthesis insights from scientific literature via text extraction and machine learning. Chem. Mater. 29, 9436\u20139444 (2017).","journal-title":"Chem. Mater."},{"key":"1335_CR8","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.1186\/1758-2946-7-S1-S3","volume":"7","author":"R Leaman","year":"2015","unstructured":"Leaman, R., Wei, C. H. & Lu, Z. TmChem: a high performance approach for chemical named entity recognition and normalization. J. Cheminform. 7, S3 (2015).","journal-title":"J. Cheminform."},{"key":"1335_CR9","doi-asserted-by":"publisher","first-page":"7673","DOI":"10.1021\/acs.chemrev.6b00851","volume":"117","author":"M Krallinger","year":"2017","unstructured":"Krallinger, M., Rabal, O., Louren\u00e7o, A., Oyarzabal, J. & Valencia, A. Information retrieval and text mining technologies for chemistry. Chem. Rev. 117, 7673\u20137761 (2017).","journal-title":"Chem. Rev."},{"key":"1335_CR10","doi-asserted-by":"crossref","unstructured":"Spangler, S. et al. Automated hypothesis generation based on mining scientific literature. In Proc. 20th ACM SIGKDD Intl Conf. Knowledge Discovery and Data Mining 1877\u20131886 (ACM, 2014).","DOI":"10.1145\/2623330.2623667"},{"key":"1335_CR11","unstructured":"Mikolov, T., Corrado, G., Chen, K. & Dean, J. Efficient estimation of word representations in vector space. Preprint at https:\/\/arxiv.org\/abs\/1301.3781 (2013)."},{"key":"1335_CR12","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G. & Dean, J. Distributed representations of words and phrases and their compositionality. Preprint at https:\/\/arxiv.org\/abs\/1310.4546 (2013)."},{"key":"1335_CR13","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R. & Manning, C. GloVe: global vectors for word representation. Proc. 2014 Conf. Empirical Methods in Natural Language Processing (EMNLP) 1532\u20131543 (Association for Computational Linguistics, 2014).","DOI":"10.3115\/v1\/D14-1162"},{"key":"1335_CR14","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.mtphys.2017.06.001","volume":"1","author":"W Liu","year":"2017","unstructured":"Liu, W. et al. New trends, strategies and opportunities in thermoelectric materials: a perspective. Materials Today Physics 1, 50\u201360 (2017).","journal-title":"Materials Today Physics"},{"key":"1335_CR15","doi-asserted-by":"publisher","first-page":"eaak9997","DOI":"10.1126\/science.aak9997","volume":"357","author":"J He","year":"2017","unstructured":"He, J. & Tritt, T. M. Advances in thermoelectric materials research: looking back and moving forward. Science 357, eaak9997 (2017).","journal-title":"Science"},{"key":"1335_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.85","volume":"4","author":"F Ricci","year":"2017","unstructured":"Ricci, F. et al. An ab initio electronic transport database for inorganic materials. Sci. Data 4, 170085 (2017).","journal-title":"Sci. Data"},{"key":"1335_CR17","doi-asserted-by":"publisher","first-page":"B864","DOI":"10.1103\/PhysRev.136.B864","volume":"136","author":"P Hohenberg","year":"1964","unstructured":"Hohenberg, P. & Kohn, W. Inhomogeneous electron gas. Phys. Rev. 136, B864\u2013B871 (1964).","journal-title":"Phys. Rev."},{"key":"1335_CR18","doi-asserted-by":"publisher","first-page":"A1133","DOI":"10.1103\/PhysRev.140.A1133","volume":"140","author":"W Kohn","year":"1965","unstructured":"Kohn, W. & Sham, L. J. Self-consistent equations including exchange and correlation effects. Phys. Rev. 140, A1133\u2013A1138 (1965).","journal-title":"Phys. Rev."},{"key":"1335_CR19","doi-asserted-by":"publisher","first-page":"2911","DOI":"10.1021\/cm400893e","volume":"25","author":"MW Gaultois","year":"2013","unstructured":"Gaultois, M. W. et al. Data-driven review of thermoelectric materials: performance and resource onsiderations. Chem. Mater. 25, 2911\u20132920 (2013).","journal-title":"Chem. Mater."},{"key":"1335_CR20","doi-asserted-by":"publisher","first-page":"72","DOI":"10.2307\/1412159","volume":"15","author":"C Spearman","year":"1904","unstructured":"Spearman, C. The proof and measurement of association between two things. Am. J. Psychol. 15, 72\u2013101 (1904).","journal-title":"Am. J. Psychol."},{"key":"1335_CR21","doi-asserted-by":"publisher","first-page":"3622","DOI":"10.1002\/adma.201200732","volume":"24","author":"T Plirdpring","year":"2012","unstructured":"Plirdpring, T. et al. Chalcopyrite CuGaTe2: a high-efficiency bulk thermoelectric material. Adv. Mater. 24, 3622\u20133626 (2012).","journal-title":"Adv. Mater."},{"key":"1335_CR22","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1016\/j.nantod.2016.10.003","volume":"11","author":"H Tian","year":"2016","unstructured":"Tian, H. et al. Low-symmetry two-dimensional materials for electronic and photonic applications. Nano Today 11, 763\u2013777 (2016).","journal-title":"Nano Today"},{"key":"1335_CR23","doi-asserted-by":"publisher","first-page":"110009","DOI":"10.1063\/1.4980633","volume":"1832","author":"C Pandey","year":"2017","unstructured":"Pandey, C., Sharma, R. & Sharma, Y. Thermoelectric properties of defect chalcopyrites. AIP Conf. Proc. 1832, 110009 (2017).","journal-title":"AIP Conf. Proc."},{"key":"1335_CR24","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1038\/nature13184","volume":"508","author":"L-D Zhao","year":"2014","unstructured":"Zhao, L.-D. et al. Ultralow thermal conductivity and high thermoelectric figure of merit in SnSe crystals. Nature 508, 373\u2013377 (2014).","journal-title":"Nature"},{"key":"1335_CR25","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. Preprint at https:\/\/arxiv.org\/abs\/1810.04805 (2018)."},{"key":"1335_CR26","unstructured":"Peters, M. E. et al. Deep contextualized word representations. Preprint at https:\/\/arxiv.org\/abs\/1802.05365 (2018)."},{"key":"1335_CR27","doi-asserted-by":"publisher","first-page":"011002","DOI":"10.1063\/1.4812323","volume":"1","author":"A Jain","year":"2013","unstructured":"Jain, A. et al. The materials project: a materials genome approach to accelerating materials innovation. APL Mater. 1, 011002 (2013).","journal-title":"APL Mater."},{"key":"1335_CR28","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.commatsci.2012.10.028","volume":"68","author":"SP Ong","year":"2013","unstructured":"Ong, S. P. et al. Python Materials Genomics (pymatgen): a robust, open-source Python library for materials analysis. Comput. Mater. Sci. 68, 314\u2013319 (2013).","journal-title":"Comput. Mater. Sci."},{"key":"1335_CR29","doi-asserted-by":"publisher","first-page":"1758","DOI":"10.1103\/PhysRevB.59.1758","volume":"59","author":"G Kresse","year":"1999","unstructured":"Kresse, G. & Joubert, D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. Rev. B Condens. Matter Mater. Phys. 59, 1758\u20131775 (1999).","journal-title":"Phys. Rev. B Condens. Matter Mater. Phys."},{"key":"1335_CR30","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","volume":"77","author":"JP Perdew","year":"1996","unstructured":"Perdew, J. P., Burke, K. & Ernzerhof, M. Generalized gradient approximation made simple. Phys. Rev. Lett. 77, 3865\u20133868 (1996).","journal-title":"Phys. Rev. Lett."},{"key":"1335_CR31","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1103\/PhysRevB.54.11169","volume":"54","author":"G Kresse","year":"1996","unstructured":"Kresse, G. & Furthm\u00fcller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. Rev. B Condens. Matter 54, 11169\u201311186 (1996).","journal-title":"Phys. Rev. B Condens. Matter"},{"key":"1335_CR32","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/0927-0256(96)00008-0","volume":"6","author":"G Kresse","year":"1996","unstructured":"Kresse, G. & Furthm\u00fcller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. Mater. Sci. 6, 15\u201350 (1996).","journal-title":"Comput. Mater. Sci."},{"key":"1335_CR33","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.cpc.2006.03.007","volume":"175","author":"GK Madsen","year":"2006","unstructured":"Madsen, G. K. & Singh, D. J. Boltztrap. A code for calculating band-structure dependent quantities. Comput. Phys. Commun. 175, 67\u201371 (2006).","journal-title":"Comput. Phys. Commun."},{"key":"1335_CR34","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.commatsci.2017.07.030","volume":"139","author":"K Mathew","year":"2017","unstructured":"Mathew, K. et al. Atomate: a high-level interface to generate, execute, and analyze computational materials science workflows. Comput. Mater. Sci. 139, 140\u2013152 (2017).","journal-title":"Comput. Mater. Sci."},{"key":"1335_CR35","doi-asserted-by":"publisher","first-page":"5037","DOI":"10.1002\/cpe.3505","volume":"27","author":"A Jain","year":"2013","unstructured":"Jain, A. et al. Fireworks: a dynamic workflow system designed for high-throughput applications. Concurr. Comput. 27, 5037\u20135059 (2013).","journal-title":"Concurr. Comput."},{"key":"1335_CR36","doi-asserted-by":"publisher","first-page":"425401","DOI":"10.1088\/1361-648X\/aade17","volume":"30","author":"X Yang","year":"2018","unstructured":"Yang, X., Dai, Z., Zhao, Y., Liu, J. & Meng, S. Low lattice thermal conductivity and excellent thermoelectric behavior in Li3Sb and Li3Bi. J. Phys. Condens. Matter 30, 425401 (2018).","journal-title":"J. Phys. Condens. Matter"},{"key":"1335_CR37","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/j.physe.2018.12.004","volume":"108","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Gao, Z. & Zhou, J. Ultralow lattice thermal conductivity and electronic properties of monolayer 1T phase semimetal SiTe2 and SnTe2. Physica E 108, 53\u201359 (2019).","journal-title":"Physica E"},{"key":"1335_CR38","doi-asserted-by":"publisher","first-page":"29150","DOI":"10.1021\/acs.jpcc.8b10564","volume":"122","author":"M Mukherjee","year":"2018","unstructured":"Mukherjee, M., Yumnam, G. & Singh, A. K. High thermoelectric figure of merit via tunable valley convergence coupled low thermal conductivity in $${{\\rm{A}}}^{{\\rm{I}}{\\rm{I}}}{{\\rm{B}}}^{{\\rm{I}}{\\rm{V}}}{{\\rm{C}}}_{2}^{{\\rm{V}}}$$ chalcopyrites. J. Phys. Chem. C 122, 29150\u201329157 (2018).","journal-title":"J. Phys. Chem. C"},{"key":"1335_CR39","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.127","volume":"4","author":"E Kim","year":"2017","unstructured":"Kim, E. et al. Machine-learned and codified synthesis parameters of oxide materials. Sci. Data 4, 170127 (2017).","journal-title":"Sci. Data"},{"key":"1335_CR40","doi-asserted-by":"publisher","first-page":"135502","DOI":"10.1103\/PhysRevLett.117.135502","volume":"117","author":"FA Faber","year":"2016","unstructured":"Faber, F. A., Lindmaa, A., Von Lilienfeld, O. A. & Armiento, R. Machine learning energies of 2 million elpasolite (ABC2D6) crystals. Phys. Rev. Lett. 117, 135502 (2016).","journal-title":"Phys. Rev. Lett."},{"key":"1335_CR41","doi-asserted-by":"publisher","first-page":"E6411","DOI":"10.1073\/pnas.1801181115","volume":"115","author":"Q Zhou","year":"2018","unstructured":"Zhou, Q. et al. Learning atoms for materials discovery. Proc. Natl Acad. Sci. USA 115, E6411\u2013E6417 (2018).","journal-title":"Proc. Natl Acad. Sci. USA"}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41586-019-1335-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-019-1335-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41586-019-1335-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T08:23:25Z","timestamp":1732782205000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41586-019-1335-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,3]]},"references-count":41,"journal-issue":{"issue":"7763","published-print":{"date-parts":[[2019,7,4]]}},"alternative-id":["1335"],"URL":"https:\/\/doi.org\/10.1038\/s41586-019-1335-8","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,3]]},"assertion":[{"value":"19 December 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2019","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"}}]}}