{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:34:24Z","timestamp":1775230464157,"version":"3.50.1"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["MA 3964\/8-2"],"award-info":[{"award-number":["MA 3964\/8-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["MA 3964\/8-2"],"award-info":[{"award-number":["MA 3964\/8-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["STA 572\/14-2"],"award-info":[{"award-number":["STA 572\/14-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Digit Libr"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s00799-024-00404-6","type":"journal-article","created":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T20:10:30Z","timestamp":1718914230000},"page":"841-853","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Comparing free reference extraction pipelines"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2492-5297","authenticated-orcid":false,"given":"Tobias","family":"Backes","sequence":"first","affiliation":[]},{"given":"Anastasiia","family":"Iurshina","sequence":"additional","affiliation":[]},{"given":"Muhammad Ahsan","family":"Shahid","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6656-1658","authenticated-orcid":false,"given":"Philipp","family":"Mayr","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,20]]},"reference":[{"key":"404_CR1","unstructured":"Ashok, D., Zachary, C.: Lipton. PromptNER: Prompting For Named Entity Recognition, June (2023). arXiv:2305.15444 [cs]"},{"key":"404_CR2","unstructured":"Birkeneder, B., Aufenvenne, P., Haase, C., Mayr, P., Steinbrink M.: Extracting literature references in German Speaking Geography\u2014the GEOcite project. In: Proceedings of the Workshop on Understanding LIterature references in academic full TExt, pp. 34\u201341. CEUR-WS.org (2022). http:\/\/ceur-ws.org\/Vol-3220\/paper4.pdf"},{"key":"404_CR3","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/978-3-031-16802-4_24","volume-title":"Linking Theory and Practice of Digital Libraries","author":"T Borst","year":"2022","unstructured":"Borst, T., Mielck, J., Nannt, M., Riese, W.: Extracting funder information from scientific papers\u2014experiences with question answering. In: Silvello, G., Corcho, O., Manghi, P., Nunzio, G.M.D., Golub, K., Ferro, N., Poggi, A. (eds.) Linking Theory and Practice of Digital Libraries, vol. 13541, pp. 289\u2013296. Springer, Cham (2022)"},{"key":"404_CR4","doi-asserted-by":"publisher","unstructured":"Boukhers, Z., Ambhore,S., Staab, S.: An end-to-end approach for extracting and segmenting high-variance references from pdf documents. In: 2019 ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp. 186\u2013195 (2019). https:\/\/doi.org\/10.1109\/JCDL.2019.00035","DOI":"10.1109\/JCDL.2019.00035"},{"key":"404_CR5","unstructured":"Carta, S., Giuliani, A., Piano, L., Podda, A.S., Pompianu, L., Tiddia, S.G.: Iterative zero-shot LLM prompting for knowledge graph construction. arXiv, July 2023. arXiv:2307.01128 [cs]"},{"issue":"2","key":"404_CR6","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TKDE.2010.231","volume":"24","author":"C-C Chen","year":"2010","unstructured":"Chen, C.-C., Yang, K.-H., Chen, C.-L., Ho, J.-M.: Bibpro: a citation parser based on sequence alignment. IEEE Trans. Knowl. Data Eng. 24(2), 236\u2013250 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"404_CR7","doi-asserted-by":"publisher","unstructured":"Cioffi, A., Peroni, S.: Structured references from pdf articles: assessing the tools for bibliographic reference extraction and parsing. In: Linking Theory and Practice of Digital Libraries: 26th International Conference on Theory and Practice of Digital Libraries, TPDL 2022, Padua, Italy, September 20\u201323, (2022), Proceedings, pp. 425\u2013432. Springer, Berlin (2022). ISBN 978-3-031-16801-7. https:\/\/doi.org\/10.1007\/978-3-031-16802-4_42","DOI":"10.1007\/978-3-031-16802-4_42"},{"key":"404_CR8","doi-asserted-by":"publisher","DOI":"10.5334\/johd.9","author":"G Colavizza","year":"2017","unstructured":"Colavizza, G., Romanello, M.: Annotated references in the historiography on Venice: 19th\u201321st centuries. J. Open Human. Data (2017). https:\/\/doi.org\/10.5334\/johd.9","journal-title":"J. Open Human. Data"},{"key":"404_CR9","doi-asserted-by":"crossref","unstructured":"Constantin, A., Pettifer, S., Voronkov, A.: Pdfx: fully-automated pdf-to-xml conversion of scientific literature. In: Proceedings of the 2013 ACM Symposium on Document Engineering, pp. 177\u2013180 (2013)","DOI":"10.1145\/2494266.2494271"},{"key":"404_CR10","doi-asserted-by":"crossref","unstructured":"Cortez, E., da Silva, A.S., Gon\u00e7alves, M.A., Mesquita, F., de\u00a0Moura, E.S.: Flux-cim: flexible unsupervised extraction of citation metadata. In: Proceedings of the 7th ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 215\u2013224 (2007)","DOI":"10.1145\/1255175.1255219"},{"issue":"6","key":"404_CR11","doi-asserted-by":"publisher","first-page":"1144","DOI":"10.1002\/asi.21049","volume":"60","author":"E Cortez","year":"2009","unstructured":"Cortez, E., da Silva, A.S., Gon\u00e7alves, M.A., Mesquita, F., de Moura, E.S.: A flexible approach for extracting metadata from bibliographic citations. J. Am. Soc. Inform. Sci. Technol. 60(6), 1144\u20131158 (2009)","journal-title":"J. Am. Soc. Inform. Sci. Technol."},{"key":"404_CR12","first-page":"661","volume":"8","author":"IG Councill","year":"2008","unstructured":"Councill, I.G., Giles, C.L., Kan, M.-Y.: Parscit: an open-source CRF reference string parsing package. InLREC 8, 661\u2013667 (2008)","journal-title":"InLREC"},{"key":"404_CR13","doi-asserted-by":"crossref","unstructured":"Cuong, N.V., Chandrasekaran, M.K., Kan, M.-Y., Lee, W.S.: Scholarly document information extraction using extensible features for efficient higher order semi-CRFS. In: Proceedings of the 15th ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 61\u201364 (2015)","DOI":"10.1145\/2756406.2756946"},{"issue":"1","key":"404_CR14","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","volume":"15","author":"J Dagdelen","year":"2024","unstructured":"Dagdelen, J., Dunn, A., Lee, S., Walker, N., Rosen, A.S., Ceder, G., Persson, K.A., Jain, A.: Structured information extraction from scientific text with large language models. Nat. Commun. 15(1), 1418 (2024)","journal-title":"Nat. Commun."},{"key":"404_CR15","doi-asserted-by":"publisher","unstructured":"Daquino, M., Peroni, S., Shotton, D., Colavizza, G., Ghavimi, B., Lauscher, A., Mayr, P., Romanello, M., Zumstein, P.: The OpenCitations data model. In: Proceedings of International Semantic Web Conference (ISWC 2020), pp. 447\u2013463. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-62466-8_28. https:\/\/arxiv.org\/abs\/2005.11981","DOI":"10.1007\/978-3-030-62466-8_28"},{"issue":"1","key":"404_CR16","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.dss.2006.08.006","volume":"43","author":"M-Y Day","year":"2007","unstructured":"Day, M.-Y., Tsai, R.T.-H., Sung, C.-L., Hsieh, C.-C., Lee, C.-W., Shih-Hung, W., Kun-Pin, W., Ong, C.-S., Hsu, W.-L.: Reference metadata extraction using a hierarchical knowledge representation framework. Decis. Support Syst. 43(1), 152\u2013167 (2007)","journal-title":"Decis. Support Syst."},{"issue":"3159","key":"404_CR17","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1126\/science.122.3159.108","volume":"122","author":"E Garfield","year":"1955","unstructured":"Garfield, E.: Citation indexes for science. Science 122(3159), 108\u2013111 (1955). https:\/\/doi.org\/10.1126\/science.122.3159.108","journal-title":"Science"},{"issue":"01","key":"404_CR18","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1142\/S0218001401000836","volume":"15","author":"Z Ghahramani","year":"2001","unstructured":"Ghahramani, Z.: An introduction to hidden Markov models and Bayesian networks. Int. J. Pattern Recognit. Artif. Intell. 15(01), 9\u201342 (2001)","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"404_CR19","unstructured":"Goel, A., Gueta, A., Gilon, O., Liu, C., Erell, S., Nguyen, L.H., Hao, X., Jaber, B., Reddy, S., Kartha, R. et\u00a0al.: LLMS accelerate annotation for medical information extraction. In: Machine Learning for Health (ML4H), pp. 82\u2013100. PMLR (2023)"},{"key":"404_CR20","unstructured":"Grennan, M., Beel, J.: Synthetic vs. real reference strings for citation parsing, and the importance of re-training and out-of-sample data for meaningful evaluations: experiments with GROBID, GIANT and CORA. In: Knoth, P., Stahl, C., Gyawali, B., Pride, D., Kunnath, S. N., Herrmannova, D. (eds) Proceedings of the 8th International Workshop on Mining Scientific Publications, pp. 27\u201335, Wuhan, China, 05 August 2020. Association for Computational Linguistics. https:\/\/aclanthology.org\/2020.wosp-1.4"},{"key":"404_CR21","unstructured":"Grennan, M., Schibel, M., Collins, A., Beel, J.: Giant: The 1-billion annotated synthetic bibliographic-reference-string dataset for deep citation parsing. In: 27th AIAI Irish Conference on Artificial Intelligence and Cognitive Science, pp. 101\u2013112 (2019)"},{"issue":"2","key":"404_CR22","first-page":"6","volume":"31","author":"T Groza","year":"2012","unstructured":"Groza, T., Astrand, G., Handschuh, S.: Reference information extraction and processing using random conditional fields. Inf. Technol. Lib. 31(2), 6\u201320 (2012)","journal-title":"Inf. Technol. Lib."},{"key":"404_CR23","doi-asserted-by":"crossref","unstructured":"Guo, Z., Jin, H.: Reference metadata extraction from scientific papers. In: 2011 12th International Conference on Parallel and Distributed Computing, Applications and Technologies, pp. 45\u201349. IEEE (2011)","DOI":"10.1109\/PDCAT.2011.72"},{"key":"404_CR24","doi-asserted-by":"crossref","unstructured":"Gupta, D., Morris, B., Catapano, T., Sautter, G.: A new approach towards bibliographic reference identification, parsing and inline citation matching. In: International Conference on Contemporary Computing, pp. 93\u2013102. Springer (2009)","DOI":"10.1007\/978-3-642-03547-0_10"},{"key":"404_CR25","doi-asserted-by":"crossref","unstructured":"Hadi, M.U., Qureshi, R., Shah, A., Irfan, M., Zafar, A., Shaikh, M.B., Akhtar, N., Wu, J., Mirjalili, S., et\u00a0al.: A survey on large language models: applications, challenges, limitations, and practical usage. Authorea Preprints (2023)","DOI":"10.36227\/techrxiv.23589741.v1"},{"key":"404_CR26","doi-asserted-by":"crossref","unstructured":"Hetzner, E.: A simple method for citation metadata extraction using hidden Markov models. In: Proceedings of the 8th ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 280\u2013284 (2008)","DOI":"10.1145\/1378889.1378937"},{"key":"404_CR27","doi-asserted-by":"publisher","unstructured":"Hosseini, A., Ghavimi, B., Boukhers, Z., Mayr, P.: Excite\u2014a toolchain to extract, match and publish open literature references. In: 2019 ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp. 432\u2013433 (2019). https:\/\/doi.org\/10.1109\/JCDL.2019.00105","DOI":"10.1109\/JCDL.2019.00105"},{"key":"404_CR28","doi-asserted-by":"crossref","unstructured":"Hsieh, Y.-L., Liu, S.-H., Yang, T.-H., Chen, Y.-H., Chang, Y.-C., Hsieh, G., Shih, C.-W., Lu, C.-H., Hsu, W.-L.: A frame-based approach for reference metadata extraction. In: International Conference on Technologies and Applications of Artificial Intelligence, pp. 154\u2013163. Springer (2014)","DOI":"10.1007\/978-3-319-13987-6_15"},{"issue":"2","key":"404_CR29","doi-asserted-by":"publisher","first-page":"43707","DOI":"10.1162\/qss_c_00138","volume":"2","author":"BI Hutchins","year":"2021","unstructured":"Hutchins, B.I.: A tipping point for open citation data. Quant. Sci. Stud. 2(2), 43707 (2021). https:\/\/doi.org\/10.1162\/qss_c_00138","journal-title":"Quant. Sci. Stud."},{"key":"404_CR30","unstructured":"Indrawati, A., Yoganingrum, A., Yuwono, P.: Evaluating the quality of the Indonesian scientific journal references using ParsCit, CERMINE and GROBID. Lib. Philos. Pract. 1\u201314 (2019)"},{"key":"404_CR31","unstructured":"Jiang, A.Q., Sablayrolles, A., Mensch, A., Bamford, C., Chaplot, D.S., de\u00a0las Casas, D., Bressand, F., Lengyel, G., Lample, G., Saulnier, L., et\u00a0al.: Mistral 7b. arXiv preprint arXiv:2310.06825, (2023)"},{"issue":"7","key":"404_CR32","first-page":"1","volume":"18","author":"R Kern","year":"2012","unstructured":"Kern, R., Jack, K., Hristakeva, M., Granitzer, M.: Teambeam-meta-data extraction from scientific literature. D-Lib Mag. 18(7), 1 (2012)","journal-title":"D-Lib Mag."},{"key":"404_CR33","doi-asserted-by":"crossref","unstructured":"Kim, Y.-M., Bellot, P., Tavernier, J., Faath, E., Dacos, M.: Evaluation of BILBO reference parsing in digital humanities via a comparison of different tools. In: Proceedings of the 2012 ACM Symposium on Document Engineering, pp. 209\u2013212 (2012)","DOI":"10.1145\/2361354.2361400"},{"key":"404_CR34","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/978-3-319-67162-8_15","volume-title":"New Trends in Databases and Information Systems","author":"M K\u00f6rner","year":"2017","unstructured":"K\u00f6rner, M., Ghavimi, B., Mayr, P., Hartmann, H., Staab, S.: Evaluating reference string extraction using line-based conditional random fields: a case study with German language publications. In: Kirikova, M., N\u00f8rv\u00e5g, K., Papadopoulos, G.A., Gamper, J., Wrembel, R., Darmont, J., Rizzi, S. (eds.) New Trends in Databases and Information Systems, pp. 137\u2013145. Springer, Cham (2017)"},{"key":"404_CR35","unstructured":"Lafferty, J.D., McCallum, A., Fernando C.N.: Pereira. Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the 18th international conference on machine learning, ICML\u201901, pp. 282\u2013289. Morgan Kaufmann Publishers Inc, San Francisco (2001)"},{"issue":"3","key":"404_CR36","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/s11192-010-0202-z","volume":"84","author":"P Larsen","year":"2010","unstructured":"Larsen, P., Von Ins, M.: The rate of growth in scientific publication and the decline in coverage provided by science citation index. Scientometrics 84(3), 575\u2013603 (2010)","journal-title":"Scientometrics"},{"key":"404_CR37","unstructured":"Li, B., Fang, G., Yang, Y., Wang, Q., Ye, W., Zhao, W., Zhang, S.: Evaluating ChatGPT\u2019s information extraction capabilities: an assessment of performance, explainability, calibration, and faithfulness, April (2023). arXiv:2304.11633 [cs]"},{"key":"404_CR38","doi-asserted-by":"publisher","unstructured":"Lipinski, M., Yao, K., Breitinger, C., Beel, J., Gipp, B.: Evaluation of header metadata extraction approaches and tools for scientific pdf documents. In: Proceedings of the 13th ACM\/IEEE-CS Joint Conference on Digital Libraries, JCDL\u201913, pp. 385\u2013386, New York (2013). Association for Computing Machinery. ISBN 9781450320771https:\/\/doi.org\/10.1145\/2467696.2467753","DOI":"10.1145\/2467696.2467753"},{"key":"404_CR39","doi-asserted-by":"crossref","unstructured":"Lopez, P.: GROBID: Combining automatic bibliographic data recognition and term extraction for scholarship publications. In: International Conference on Theory and Practice of Digital Libraries, pp. 473\u2013474. Springer (2009)","DOI":"10.1007\/978-3-642-04346-8_62"},{"key":"404_CR40","doi-asserted-by":"crossref","unstructured":"Namikoshi, D., Ohta, M., Takasu, A., Adach, J.: CRF-based bibliography extraction from reference strings using a small amount of training data. In: 2017 12th International Conference on Digital Information Management (ICDIM), pp. 59\u201364. IEEE (2017)","DOI":"10.1109\/ICDIM.2017.8244665"},{"key":"404_CR41","doi-asserted-by":"crossref","unstructured":"Ohta, M., Arauchi, D., Takasu, A., Adachi, J.: Crf-based bibliography extraction from reference strings focusing on various token granularities. In: 2012 10th IAPR International Workshop on Document Analysis Systems, pp. 276\u2013281. IEEE (2012)","DOI":"10.1109\/DAS.2012.28"},{"key":"404_CR42","doi-asserted-by":"crossref","unstructured":"Ohta, M., Arauchi, D., Takasu, A., Adachi, J.: Empirical evaluation of CRF-based bibliography extraction from reference strings. In: 2014 11th IAPR International Workshop on Document Analysis Systems, pp. 287\u2013292. IEEE (2014)","DOI":"10.1109\/DAS.2014.64"},{"issue":"9","key":"404_CR43","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1016\/j.ins.2011.01.014","volume":"181","author":"B Ojokoh","year":"2011","unstructured":"Ojokoh, B., Zhang, M., Tang, J.: A trigram hidden Markov model for metadata extraction from heterogeneous references. Inf. Sci. 181(9), 1538\u20131551 (2011)","journal-title":"Inf. Sci."},{"key":"404_CR44","doi-asserted-by":"publisher","unstructured":"Pagnotta, O.: Refex project\u2014dataset and gold standard January (2024). https:\/\/doi.org\/10.5281\/zenodo.10524830","DOI":"10.5281\/zenodo.10524830"},{"key":"404_CR45","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.-J.: Bleu: a method for automatic evaluation of machine translation. In: Isabelle, P., Charniak, E., Lin, D. (eds) Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318, Philadelphia, Pennsylvania, USA, July (2002). Association for Computational Linguistics. https:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"issue":"4","key":"404_CR46","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1016\/j.ipm.2005.09.002","volume":"42","author":"F Peng","year":"2006","unstructured":"Peng, F., McCallum, A.: Information extraction from research papers using conditional random fields. Inf. Process. Manag. 42(4), 963\u2013979 (2006)","journal-title":"Inf. Process. Manag."},{"issue":"1","key":"404_CR47","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1162\/qss_a_00023","volume":"1","author":"S Peroni","year":"2020","unstructured":"Peroni, S., Shotton, D.: Opencitations, an infrastructure organization for open scholarship. Quant. Sci. Stud. 1(1), 428\u2013444 (2020)","journal-title":"Quant. Sci. Stud."},{"issue":"4","key":"404_CR48","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/s00799-018-0242-1","volume":"19","author":"A Prasad","year":"2018","unstructured":"Prasad, A., Kaur, M., Kan, M.-Y.: Neural parscit: a deep learning-based reference string parser. Int. J. Digit. Libr. 19(4), 323\u2013337 (2018)","journal-title":"Int. J. Digit. Libr."},{"key":"404_CR49","unstructured":"Ramshaw, L., Tarjan, R.E.: On minimum-cost assignments in unbalanced bipartite graphs. Technical report, HP Labs, Palo Alto, CA, USA (2012)"},{"issue":"7","key":"404_CR50","first-page":"46","volume":"13","author":"JW Ratcliff","year":"1988","unstructured":"Ratcliff, J.W., Metzener, D., et al.: Pattern matching: the gestalt approach. Dr. Dobb\u2019s J. 13(7), 46 (1988)","journal-title":"Dr. Dobb\u2019s J."},{"issue":"2","key":"404_CR51","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1134\/S1054661823020104","volume":"33","author":"IS Rozhkov","year":"2023","unstructured":"Rozhkov, I.S., Loukachevitch, N.V.: Prompts in few-shot named entity recognition. Pattern Recogn. Image Anal. 33(2), 122\u2013131 (2023). https:\/\/doi.org\/10.1134\/S1054661823020104","journal-title":"Pattern Recogn. Image Anal."},{"key":"404_CR52","doi-asserted-by":"publisher","unstructured":"Singh, V.K., Singh, P., Karmakar, M., Leta, J., Mayr, P.: The journal coverage of web of science, scopus and dimensions: a comparative analysis. Scientometrics 126(6), 5113\u20135142 (2021). https:\/\/doi.org\/10.1007\/s11192-021-03948-5","DOI":"10.1007\/s11192-021-03948-5"},{"issue":"2","key":"404_CR53","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s10032-006-0032-y","volume":"10","author":"C Staelin","year":"2007","unstructured":"Staelin, C., Elad, M., Greig, D., Shmueli, O., Vans, M.: Biblio: automatic meta-data extraction. IJDAR 10(2), 113\u2013126 (2007)","journal-title":"IJDAR"},{"key":"404_CR54","doi-asserted-by":"crossref","unstructured":"Suryawati, E., Widyantoro, D.H.: Combination of heuristic, rule-based and machine learning for bibliography extraction. In: 2017 5th International Conference on Instrumentation, Communications, Information Technology, and Biomedical Engineering (ICICI-BME), pp. 276\u2013281. IEEE (2017)","DOI":"10.1109\/ICICI-BME.2017.8537772"},{"key":"404_CR55","unstructured":"Tan, Z., Beigi, A., Wang, S., Guo, R., Bhattacharjee, A., Jiang, B., Karami, M., Li, J., Cheng, L., Liu, H.: Large language models for data annotation: a survey. arXiv preprint arXiv:2402.13446 (2024)"},{"key":"404_CR56","doi-asserted-by":"publisher","unstructured":"Tkaczyk, D., Szostek, P., Dendek, P.J., Fedoryszak, M., Bolikowski, L.: Cermine\u2014automatic extraction of metadata and references from scientific literature. In: 2014 11th IAPR International Workshop on Document Analysis Systems, pp. 217\u2013221 (2014). https:\/\/doi.org\/10.1109\/DAS.2014.63","DOI":"10.1109\/DAS.2014.63"},{"key":"404_CR57","unstructured":"Tkaczyk, D., Collins, A., Sheridan, P., Beel, J.: Evaluation and comparison of open source bibliographic reference parsers: a business use case. arXiv preprint arXiv:1802.01168 (2018a)"},{"key":"404_CR58","doi-asserted-by":"publisher","unstructured":"Tkaczyk, D., Collins, A., Sheridan, P., Beel, J.: Machine learning vs. rules and out-of-the-box vs. retrained: an evaluation of open-source bibliographic reference and citation parsers. In: Proceedings of the 18th ACM\/IEEE on joint conference on digital libraries, JCDL\u201918, pp. 99\u2013108, New York, NY, USA. Association for Computing Machinery (2018b). ISBN 9781450351782. https:\/\/doi.org\/10.1145\/3197026.3197048","DOI":"10.1145\/3197026.3197048"},{"key":"404_CR59","unstructured":"Tkaczyk, D., Gupta, R., Cinti, R., Beel, J.: Parsrec: a novel meta-learning approach to recommending bibliographic reference parsers. arXiv preprint arXiv:1811.10369 (2018c)"},{"key":"404_CR60","unstructured":"Tsochantaridis, I., Joachims, T., Hofmann, T., Altun, Y., Singer, Y.: Large margin methods for structured and interdependent output variables. J. Mach. Learn. Res. 6(9) (2005)"},{"key":"404_CR61","unstructured":"Victor, S., Albert, W., Colin, R., Stephen, B., Lintang, S., Zaid, A., Antoine, C., Arnaud, S., Arun, R., Manan, D. et\u00a0al.: Multitask prompted training enables zero-shot task generalization. In: International Conference on Learning Representations (2022)"},{"key":"404_CR62","unstructured":"Wang, S., Sun, X., Li, X., Ouyang, R., Wu, F., Zhang, T., Li, J., Wang, G.: GPT-NER: named entity recognition via large language models, October (2023). arXiv:2304.10428 [cs]"},{"key":"404_CR63","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., Metzler, D., et\u00a0al. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)"},{"key":"404_CR64","unstructured":"Wei, X., Cui, X., Cheng, N., Wang, X., Zhang, X., Huang, S., Xie, P., Xu, J., Chen, Y., Zhang, M., Jiang, Y., Han, W.: Zero-shot information extraction via chatting with ChatGPT, February (2023). arXiv:2302.10205 [cs]"},{"key":"404_CR65","first-page":"219","volume":"99","author":"J Weston","year":"1999","unstructured":"Weston, J., Watkins, C., et al.: Support vector machines for multi-class pattern recognition. InEsann 99, 219\u2013224 (1999)","journal-title":"InEsann"},{"issue":"7646","key":"404_CR66","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1038\/543492a","volume":"543","author":"P Wouters","year":"2017","unstructured":"Wouters, P.: Eugene Garfield (1925\u20132017). Nature 543(7646), 492\u2013492 (2017). https:\/\/doi.org\/10.1038\/543492a","journal-title":"Nature"},{"key":"404_CR67","doi-asserted-by":"crossref","unstructured":"Yin, P., Zhang, M., Deng, M., Yang, D.Q.: Metadata extraction from bibliographies using bigram hmm. In: International Conference on Asian Digital Libraries, pp. 310\u2013319. Springer (2004)","DOI":"10.1007\/978-3-540-30544-6_33"},{"issue":"4","key":"404_CR68","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.compbiomed.2011.02.005","volume":"41","author":"Q Zhang","year":"2011","unstructured":"Zhang, Q., Cao, Y.-G., Hong, Yu.: Parsing citations in biomedical articles using conditional random fields. Comput. Biol. Med. 41(4), 190\u2013194 (2011)","journal-title":"Comput. Biol. Med."},{"issue":"3","key":"404_CR69","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-12-S5-S1","volume":"12","author":"X Zhang","year":"2011","unstructured":"Zhang, X., Zou, J., Le, D.X., Thoma, G.R.: A structural SVM approach for reference parsing. BMC Bioinf. 12(3), 1\u20137 (2011)","journal-title":"BMC Bioinf."},{"key":"404_CR70","unstructured":"Zhou, W., Zhang, S., Gu, Y., Chen, M., Poon, H.: UniversalNER: targeted distillation from large language models for open named entity recognition, August (2023). arXiv:2308.03279 [cs]"},{"issue":"2","key":"404_CR71","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s10032-009-0105-9","volume":"13","author":"J Zou","year":"2010","unstructured":"Zou, J., Le, D., Thoma, G.R.: Locating and parsing bibliographic references in html medical articles. IJDAR 13(2), 107\u2013119 (2010)","journal-title":"IJDAR"}],"updated-by":[{"DOI":"10.1007\/s00799-024-00408-2","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T00:00:00Z","timestamp":1722384000000}}],"container-title":["International Journal on Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-024-00404-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00799-024-00404-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-024-00404-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:55:21Z","timestamp":1730192121000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00799-024-00404-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,20]]},"references-count":71,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["404"],"URL":"https:\/\/doi.org\/10.1007\/s00799-024-00404-6","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s00799-024-00408-2","asserted-by":"object"}]},"ISSN":["1432-5012","1432-1300"],"issn-type":[{"value":"1432-5012","type":"print"},{"value":"1432-1300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,20]]},"assertion":[{"value":"2 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2024","order":5,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":6,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":7,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s00799-024-00408-2","URL":"https:\/\/doi.org\/10.1007\/s00799-024-00408-2","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}