{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T18:05:21Z","timestamp":1762625121723,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031429408"},{"type":"electronic","value":"9783031429415"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-42941-5_34","type":"book-chapter","created":{"date-parts":[[2023,8,30]],"date-time":"2023-08-30T08:02:46Z","timestamp":1693382566000},"page":"393-406","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Text Mining Pipeline for\u00a0Mining the\u00a0Quantum Cascade Laser Properties"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7437-6735","authenticated-orcid":false,"given":"Deperias","family":"Kerre","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3708-6429","authenticated-orcid":false,"given":"Anne","family":"Laurent","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8086-8461","authenticated-orcid":false,"given":"Kenneth","family":"Maussang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0968-5742","authenticated-orcid":false,"given":"Dickson","family":"Owuor","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,31]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Kumar, S., Hu, Q., Reno, J.L.: 186 K operation of terahertz quantum-cascade lasers based on a diagonal design. Appl. Phys. Lett. 94(13), 131105 (2009). https:\/\/doi.org\/10.1063\/1.3114418","DOI":"10.1063\/1.3114418"},{"issue":"12","key":"34_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2020.e05623","volume":"6","author":"Z Vafapour","year":"2020","unstructured":"Vafapour, Z., Keshavarz, A., Ghahraloud, H.: The potential of terahertz sensing for cancer diagnosis. Heliyon 6(12), e05623 (2020). https:\/\/doi.org\/10.1016\/j.heliyon.2020.e05623","journal-title":"Heliyon"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Shur, M., Liu, X.: Biomedical applications of terahertz technology. In: Advances in Terahertz Biomedical Imaging and Spectroscopy, vol. 11975, p. 1197502. SPIE, March 2022. https:\/\/doi.org\/10.1117\/12.2604800","DOI":"10.1117\/12.2604800"},{"issue":"12","key":"34_CR4","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1103\/PhysRevMaterials.4.123802","volume":"98","author":"A Kanno","year":"2015","unstructured":"Kanno, A., et al.: High-speed coherent transmission using advanced photonics in terahertz bands. IEICE Trans. Electron. 98(12), 1071\u20131080 (2015). https:\/\/doi.org\/10.1103\/PhysRevMaterials.4.123802","journal-title":"IEICE Trans. Electron."},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Rosati, E.: The exception for text and data mining (TDM) in the proposed Directive on copyright in the Digital Single Market-technical aspects. Briefing Requested by the Juri Committee, European Parliament (2018). https:\/\/doi.org\/10.1093\/jiplp\/jpy063","DOI":"10.1093\/jiplp\/jpy063"},{"issue":"12","key":"34_CR6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.4.123802","volume":"4","author":"H Liang","year":"2020","unstructured":"Liang, H., Stanev, V., Kusne, A.G., Takeuchi, I.: CRYSPNet: crystal structure predictions via neural networks. Phys. Rev. Mater. 4(12), 123802 (2020). https:\/\/doi.org\/10.1103\/PhysRevMaterials.4.123802","journal-title":"Phys. Rev. Mater."},{"issue":"10","key":"34_CR7","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(10), 1894\u20131904 (2016). https:\/\/doi.org\/10.1021\/acs.jcim.6b00207","journal-title":"J. Chem. Inf. Model."},{"key":"34_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-3-17","volume":"3","author":"L Hawizy","year":"2011","unstructured":"Hawizy, L., Jessop, D.M., Adams, N., Murray-Rust, P.: ChemicalTagger: a tool for semantic text-mining in chemistry. J. Cheminform. 3, 1\u201313 (2011). https:\/\/doi.org\/10.1186\/1758-2946-3-17","journal-title":"J. Cheminform."},{"issue":"11","key":"34_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-9-S11-S4","volume":"9","author":"P Corbett","year":"2008","unstructured":"Corbett, P., Copestake, A.: Cascaded classifiers for confidence-based chemical named entity recognition. BMC Bioinform. 9(11), 1\u201310 (2008). https:\/\/doi.org\/10.1186\/1471-2105-9-S11-S4","journal-title":"BMC Bioinform."},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Remesal, M., Garc\u00eda-Ruiz, A., Prez-Rey, D., De La Iglesia, D., Maojo, V.: Using nanoinformatics methods for automatically identifying relevant nanotoxicology entities from the literature. BioMed Res. Int. 2013 (2013). https:\/\/doi.org\/10.1155\/2013\/410294","DOI":"10.1155\/2013\/410294"},{"key":"34_CR11","unstructured":"Lafferty, J., McCallum, A., Pereira, F.C.: Conditional random fields: probabilistic models for segmenting and labeling sequence data (2001)"},{"issue":"8","key":"34_CR12","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997). https:\/\/doi.org\/10.1162\/neco.1997.9.8.1735","journal-title":"Neural Comput."},{"issue":"1","key":"34_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-7-S1-S5","volume":"7","author":"DM Lowe","year":"2015","unstructured":"Lowe, D.M., Sayle, R.A.: LeadMine: a grammar and dictionary driven approach to entity recognition. J. Cheminform. 7(1), 1\u20139 (2015). https:\/\/doi.org\/10.1186\/1758-2946-7-S1-S5","journal-title":"J. Cheminform."},{"issue":"1","key":"34_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-3-41","volume":"3","author":"DM Jessop","year":"2011","unstructured":"Jessop, D.M., Adams, S.E., Willighagen, E.L., Hawizy, L., Murray-Rust, P.: OSCAR4: a flexible architecture for chemical text-mining. J. Cheminform. 3(1), 1\u201312 (2011). https:\/\/doi.org\/10.1186\/1758-2946-3-41","journal-title":"J. Cheminform."},{"issue":"12","key":"34_CR15","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1093\/bioinformatics\/bts183","volume":"28","author":"T Rockt\u00e4schel","year":"2012","unstructured":"Rockt\u00e4schel, T., Weidlich, M., Leser, U.: ChemSpot: a hybrid system for chemical named entity recognition. Bioinformatics 28(12), 1633\u20131640 (2012). https:\/\/doi.org\/10.1093\/bioinformatics\/bts183","journal-title":"Bioinformatics"},{"issue":"1","key":"34_CR16","doi-asserted-by":"publisher","first-page":"1","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(1), 1\u201310 (2015). https:\/\/doi.org\/10.1186\/1758-2946-7-S1-S3","journal-title":"J. Cheminform."},{"issue":"1","key":"34_CR17","doi-asserted-by":"publisher","first-page":"193","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(1), 193 (2022). https:\/\/doi.org\/10.1038\/s41597-022-01294-6","journal-title":"Sci. Data"},{"issue":"1","key":"34_CR18","doi-asserted-by":"publisher","first-page":"648","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(1), 648 (2022). https:\/\/doi.org\/10.1038\/s41597-022-01752-1","journal-title":"Sci. Data"},{"issue":"1","key":"34_CR19","doi-asserted-by":"publisher","first-page":"260","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(1), 260 (2020). https:\/\/doi.org\/10.1038\/s41597-020-00602-2","journal-title":"Sci. Data"},{"issue":"1","key":"34_CR20","doi-asserted-by":"publisher","first-page":"192","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(1), 192 (2022). https:\/\/doi.org\/10.1038\/s41597-022-01295-5","journal-title":"Sci. Data"},{"issue":"1","key":"34_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2018.111","volume":"5","author":"CJ Court","year":"2018","unstructured":"Court, C.J., Cole, J.M.: Auto-generated materials database of Curie and N\u00e9el temperatures via semi-supervised relationship extraction. Sci. Data 5(1), 1\u201312 (2018). https:\/\/doi.org\/10.1038\/sdata.2018.111","journal-title":"Sci. Data"},{"issue":"9","key":"34_CR22","doi-asserted-by":"publisher","first-page":"4280","DOI":"10.1021\/acs.jcim.1c00446","volume":"61","author":"J Mavracic","year":"2021","unstructured":"Mavracic, J., Court, C.J., Isazawa, T., Elliott, S.R., Cole, J.M.: ChemDataExtractor 2.0: autopopulated ontologies for materials science. J. Chem. Inf. Model. 61(9), 4280\u20134289 (2021). https:\/\/doi.org\/10.1021\/acs.jcim.1c00446","journal-title":"J. Chem. Inf. Model."},{"issue":"18","key":"34_CR23","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. Mater. 32(18), 7861\u20137873 (2020). https:\/\/doi.org\/10.1021\/acs.chemmater.0c02553","journal-title":"Chem. Mater."},{"issue":"9","key":"34_CR24","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. Inf. Model. 59(9), 3692\u20133702 (2019). https:\/\/doi.org\/10.1021\/acs.jcim.9b00470","journal-title":"J. Chem. Inf. Model."},{"issue":"1","key":"34_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-018-0280-0","volume":"10","author":"I Korvigo","year":"2018","unstructured":"Korvigo, I., Holmatov, M., Zaikovskii, A., Skoblov, M.: Putting hands to rest: efficient deep CNN-RNN architecture for chemical named entity recognition with no hand-crafted rules. J. Chem. 10(1), 1\u201310 (2018). https:\/\/doi.org\/10.1186\/s13321-018-0280-0","journal-title":"J. Chem."},{"issue":"1","key":"34_CR26","doi-asserted-by":"publisher","first-page":"203","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(1), 203 (2019). https:\/\/doi.org\/10.1038\/s41597-019-0224-1","journal-title":"Sci. Data"},{"issue":"1","key":"34_CR27","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1038\/s41597-022-01321-6","volume":"9","author":"K Cruse","year":"2022","unstructured":"Cruse, K., et al.: Text-mined dataset of gold nanoparticle synthesis procedures, morphologies, and size entities. Sci. Data 9(1), 234 (2022). https:\/\/doi.org\/10.1038\/s41597-022-01321-6","journal-title":"Sci. Data"},{"issue":"24","key":"34_CR28","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. Inf. Model. 62(24), 6365\u20136377 (2022). https:\/\/doi.org\/10.1021\/acs.jcim.2c00035","journal-title":"J. Chem. Inf. Model."},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, J., Huang, S., Cole, J.M.: OpticalBERT and OpticalTable-SQA: text-and table-based language models for the optical-materials domain. J. Chem. Inf. Model. (2023). https:\/\/doi.org\/10.1021\/acs.jcim.2c01259","DOI":"10.1021\/acs.jcim.2c01259"},{"key":"34_CR30","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s10032-019-00317-0","volume":"22","author":"N Milosevic","year":"2019","unstructured":"Milosevic, N., Gregson, C., Hernandez, R., Nenadic, G.: A framework for information extraction from tables in biomedical literature. Int. J. Doc. Anal. Recognit. (IJDAR) 22, 55\u201378 (2019). https:\/\/doi.org\/10.1007\/s10032-019-00317-0","journal-title":"Int. J. Doc. Anal. Recognit. (IJDAR)"},{"issue":"5","key":"34_CR31","doi-asserted-by":"publisher","first-page":"2492","DOI":"10.1021\/acs.jcim.9b00734","volume":"60","author":"KT Mukaddem","year":"2019","unstructured":"Mukaddem, K.T., Beard, E.J., Yildirim, B., Cole, J.M.: ImageDataExtractor: a tool to extract and quantify data from microscopy images. J. Chem. Inf. Model. 60(5), 2492\u20132509 (2019). https:\/\/doi.org\/10.1021\/acs.jcim.9b00734","journal-title":"J. Chem. Inf. Model."},{"issue":"37","key":"34_CR32","doi-asserted-by":"publisher","first-page":"19461","DOI":"10.1039\/D0NR04140H","volume":"12","author":"H Kim","year":"2020","unstructured":"Kim, H., Han, J., Han, T.Y.J.: Machine vision-driven automatic recognition of particle size and morphology in SEM images. Nanoscale 12(37), 19461\u201319469 (2020). https:\/\/doi.org\/10.1039\/D0NR04140H","journal-title":"Nanoscale"}],"container-title":["Communications in Computer and Information Science","New Trends in Database and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-42941-5_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T18:29:37Z","timestamp":1710268177000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-42941-5_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031429408","9783031429415"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-42941-5_34","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The source code and the materials used for the production of this work are publicly available at our GitHub repository: .","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Availability of Materials"}},{"value":"ADBIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Advances in Databases and Information Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Barcelona","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adbis2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/adbis.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"25","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"18% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"N\/A","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"N\/A","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}