{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T12:42:06Z","timestamp":1783341726489,"version":"3.54.6"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031280313","type":"print"},{"value":"9783031280320","type":"electronic"}],"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\/978-3-031-28032-0_31","type":"book-chapter","created":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T08:04:19Z","timestamp":1678349059000},"page":"383-405","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A Benchmark of\u00a0PDF Information Extraction Tools Using a\u00a0Multi-task and\u00a0Multi-domain Evaluation Framework for\u00a0Academic Documents"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4648-8198","authenticated-orcid":false,"given":"Norman","family":"Meuschke","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Apurva","family":"Jagdale","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3471-4127","authenticated-orcid":false,"given":"Timo","family":"Spinde","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3220-8749","authenticated-orcid":false,"given":"Jelena","family":"Mitrovi\u0107","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6522-3019","authenticated-orcid":false,"given":"Bela","family":"Gipp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,10]]},"reference":[{"key":"31_CR1","doi-asserted-by":"publisher","first-page":"99458","DOI":"10.1109\/ACCESS.2020.2997907","volume":"8","author":"MW Ahmed","year":"2020","unstructured":"Ahmed, M.W., Afzal, M.T.: FLAG-PDFe: features oriented metadata extraction framework for scientific publications. IEEE Access 8, 99458\u201399469 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2997907","journal-title":"IEEE Access"},{"key":"31_CR2","doi-asserted-by":"publisher","unstructured":"Aiello, M., Monz, C., Todoran, L., Worring, M.: Document understanding for a broad class of documents. Int. J. Doc. Anal. Recogn. 5(1),1\u201316 (2002). https:\/\/doi.org\/10.1007\/s10032-002-0080-x","DOI":"10.1007\/s10032-002-0080-x"},{"key":"31_CR3","doi-asserted-by":"publisher","unstructured":"Anzaroot, S., Passos, A., Belanger, D., McCallum, A.: Learning soft linear constraints with application to citation field extraction. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 593\u2013602. Association for Computational Linguistics, Baltimore, Maryland (2014). https:\/\/doi.org\/10.3115\/v1\/P14-1056","DOI":"10.3115\/v1\/P14-1056"},{"key":"31_CR4","doi-asserted-by":"publisher","unstructured":"Azimjonov, J., Alikhanov, J.: Rule based metadata extraction framework from academic articles. arXiv CoRR 1807.09009v1 [cs.IR], pp. 1\u201310 (2018). https:\/\/doi.org\/10.48550\/arXiv.1807.09009","DOI":"10.48550\/arXiv.1807.09009"},{"key":"31_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1007\/978-3-642-41154-0_30","volume-title":"Web Information Systems Engineering \u2013 WISE 2013","author":"H Bast","year":"2013","unstructured":"Bast, H., Korzen, C.: The Icecite research paper management system. In: Lin, X., Manolopoulos, Y., Srivastava, D., Huang, G. (eds.) WISE 2013. LNCS, vol. 8181, pp. 396\u2013409. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-41154-0_30"},{"key":"31_CR6","doi-asserted-by":"publisher","unstructured":"Bast, H., Korzen, C.: A benchmark and evaluation for text extraction from PDF. In: 2017 ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp. 1\u201310. IEEE, Toronto, ON, Canada (2017). https:\/\/doi.org\/10.1109\/JCDL.2017.7991564","DOI":"10.1109\/JCDL.2017.7991564"},{"key":"31_CR7","doi-asserted-by":"publisher","unstructured":"Bhardwaj, A., Mercier, D., Dengel, A., Ahmed, S.: DeepBIBX: deep learning for image based bibliographic data extraction. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) Neural Information Processing. ICONIP 2017. LNCS, vol. 10635, pp. 286\u2013293. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-70096-0_30","DOI":"10.1007\/978-3-319-70096-0_30"},{"issue":"2","key":"31_CR8","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1145\/376284.375682","volume":"30","author":"V Borkar","year":"2001","unstructured":"Borkar, V., Deshmukh, K., Sarawagi, S.: Automatic segmentation of text into structured records. SIGMOD Rec. 30(2), 175\u2013186 (2001). https:\/\/doi.org\/10.1145\/376284.375682","journal-title":"SIGMOD Rec."},{"key":"31_CR9","doi-asserted-by":"publisher","unstructured":"Clark, C., Divvala, S.: PDFFigures 2.0: mining figures from research papers. In: Proceedings of the 16th ACM\/IEEE-CS on Joint Conference on Digital Libraries, pp. 143\u2013152. JCDL 2016, Association for Computing Machinery, New York, NY, USA (2016). https:\/\/doi.org\/10.1145\/2910896.2910904","DOI":"10.1145\/2910896.2910904"},{"key":"31_CR10","doi-asserted-by":"publisher","unstructured":"Cortez, E., da Silva, A.S., Gon\u00e7alves, M.A., Mesquita, F., de Moura, 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. JCDL 2007, Association for Computing Machinery, New York, NY, USA (2007). https:\/\/doi.org\/10.1145\/1255175.1255219","DOI":"10.1145\/1255175.1255219"},{"issue":"6","key":"31_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. JASIST 60(6), 1144\u20131158 (2009). https:\/\/doi.org\/10.1002\/asi.21049","journal-title":"JASIST"},{"key":"31_CR12","unstructured":"Councill, I., Giles, C.L., Kan, M.Y.: ParsCit: an open-source CRF reference string parsing package. In: Proceedings of the Sixth International Conference on Language Resources and Evaluation. European Language Resources Association, Marrakech, Morocco (2008). https:\/\/aclanthology.org\/L08-1291\/"},{"key":"31_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-642-14922-1_26","volume-title":"Advanced Intelligent Computing Theories and Applications","author":"B-G Cui","year":"2010","unstructured":"Cui, B.-G., Chen, X.: An improved hidden Markov model for literature metadata extraction. In: Huang, D.-S., Zhao, Z., Bevilacqua, V., Figueroa, J.C. (eds.) ICIC 2010. LNCS, vol. 6215, pp. 205\u2013212. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-14922-1_26"},{"issue":"1","key":"31_CR14","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/j.dss.2006.08.006","volume":"43","author":"MY Day","year":"2007","unstructured":"Day, M.Y., et al.: Reference metadata extraction using a hierarchical knowledge representation framework. Decis. Support Syst. 43(1), 152\u2013167 (2007). https:\/\/doi.org\/10.1016\/j.dss.2006.08.006","journal-title":"Decis. Support Syst."},{"key":"31_CR15","doi-asserted-by":"publisher","unstructured":"De La Torre, M., Aguirre, C., Anshutz, B., Hsu, W.: MATESC: metadata-analytic text extractor and section classifier for scientific publications. In: Proceedings of the 10th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, vol. 1, pp. 261\u2013267. SciTePress (2018). https:\/\/doi.org\/10.5220\/0006937702610267","DOI":"10.5220\/0006937702610267"},{"key":"31_CR16","series-title":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/978-3-030-12981-1_29","volume-title":"Collaborative Computing: Networking, Applications and Worksharing","author":"T Fan","year":"2019","unstructured":"Fan, T., et al.: PARDA: a dataset for scholarly pdf document metadata extraction evaluation. In: Gao, H., Wang, X., Yin, Y., Iqbal, M. (eds.) CollaborateCom 2018. LNICST, vol. 268, pp. 417\u2013431. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-12981-1_29"},{"key":"31_CR17","unstructured":"F\u00e4rber, M., Thiemann, A., Jatowt, A.: A high-quality gold standard for citation-based tasks. In: Proceedings of the Eleventh International Conference on Language Resources and Evaluation. European Language Resources Association, Miyazaki, Japan (2018). https:\/\/aclanthology.org\/L18-1296"},{"key":"31_CR18","doi-asserted-by":"publisher","unstructured":"Giuffrida, G., Shek, E.C., Yang, J.: Knowledge-based metadata extraction from postscript files. In: Proceedings of the Fifth ACM Conference on Digital Libraries, pp. 77\u201384. DL 2000, Association for Computing Machinery, New York, NY, USA (2000). https:\/\/doi.org\/10.1145\/336597.336639","DOI":"10.1145\/336597.336639"},{"key":"31_CR19","doi-asserted-by":"publisher","unstructured":"Granitzer, M., Hristakeva, M., Jack, K., Knight, R.: A comparison of metadata extraction techniques for crowdsourced bibliographic metadata management. In: Proceedings of the 27th Annual ACM Symposium on Applied Computing, pp. 962\u2013964. SAC 2012, Association for Computing Machinery, New York, NY, USA (2012). https:\/\/doi.org\/10.1145\/2245276.2245462","DOI":"10.1145\/2245276.2245462"},{"key":"31_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: Proceedings of the 8th International Workshop on Mining Scientific Publications, pp. 27\u201335. Association for Computational Linguistics, Wuhan, China (2020). https:\/\/aclanthology.org\/2020.wosp-1.4"},{"key":"31_CR21","doi-asserted-by":"publisher","unstructured":"Grennan, M., Schibel, M., Collins, A., Beel, J.: GIANT: the 1-billion annotated synthetic bibliographic-reference-string dataset for deep citation parsing [Data] (2019). https:\/\/doi.org\/10.7910\/DVN\/LXQXAO","DOI":"10.7910\/DVN\/LXQXAO"},{"key":"31_CR22","doi-asserted-by":"publisher","unstructured":"Hashmi, A.M., Afzal, M.T., Rehman, S.U.: Rule based approach to extract metadata from scientific pdf documents. In: 2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA), pp. 1\u20134. IEEE, Sydney, Australia (2020). https:\/\/doi.org\/10.1109\/CITISIA50690.2020.9371784","DOI":"10.1109\/CITISIA50690.2020.9371784"},{"key":"31_CR23","doi-asserted-by":"publisher","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. JCDL 2008, Association for Computing Machinery, New York, NY, USA (2008). https:\/\/doi.org\/10.1145\/1378889.1378937","DOI":"10.1145\/1378889.1378937"},{"key":"31_CR24","unstructured":"Kasdorf, W.E.: The Columbia guide to digital publishing. Columbia University Press, USA (2003)"},{"key":"31_CR25","doi-asserted-by":"publisher","unstructured":"Kern, R., Jack, K., Hristakeva, M.: TeamBeam - meta-data extraction from scientific literature. D-Lib Magaz. 18(7\/8), 1045 (2012). https:\/\/doi.org\/10.1045\/july2012-kern","DOI":"10.1045\/july2012-kern"},{"key":"31_CR26","doi-asserted-by":"publisher","unstructured":"Klein, D., Manning, C.D.: Conditional structure versus conditional estimation in NLP models. In: Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 9\u201316. Association for Computational Linguistics, Pennsylvania, Philadelphia, PA, USA (2002). https:\/\/doi.org\/10.3115\/1118693.1118695","DOI":"10.3115\/1118693.1118695"},{"key":"31_CR27","unstructured":"Klink, S., Dengel, A., Kieninger, T.: Document structure analysis based on layout and textual features. In: IAPR International Workshop on Document Analysis Systems. IAPR, Rio de Janeiro, Brazil (2000)"},{"key":"31_CR28","series-title":"Communications in Computer and Information Science","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: N\u00f8rv\u00e5g, K., et al. (eds.) ADBIS 2017. CCIS, vol. 767, pp. 137\u2013145. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-67162-8_15"},{"key":"31_CR29","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: conditional random fields: probabilistic models for segmenting and labeling sequence data. In: Proceedings of the Eighteenth International Conference on Machine Learning, pp. 282\u2013289. ICML \u201901, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2001). https:\/\/dl.acm.org\/doi\/10.5555\/645530.655813"},{"key":"31_CR30","doi-asserted-by":"publisher","unstructured":"Ley, M.: DBLP: some lessons learned. Proc. VLDB Endow. 2(2), 1493\u20131500 (2009). https:\/\/doi.org\/10.14778\/1687553.1687577","DOI":"10.14778\/1687553.1687577"},{"key":"31_CR31","doi-asserted-by":"publisher","unstructured":"Li, M., et al.: DocBank: a benchmark dataset for document layout analysis. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 949\u2013960. International Committee on Computational Linguistics, Barcelona, Spain (Online) (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.82","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"31_CR32","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, pp. 385\u2013386. JCDL 2013, Association for Computing Machinery, New York, NY, USA (2013). https:\/\/doi.org\/10.1145\/2467696.2467753","DOI":"10.1145\/2467696.2467753"},{"issue":"17","key":"31_CR33","doi-asserted-by":"publisher","first-page":"15137","DOI":"10.1609\/aaai.v35i17.17777","volume":"35","author":"N Livathinos","year":"2021","unstructured":"Livathinos, N., et al.: Robust pdf document conversion using recurrent neural networks. Proceed. AAAI Conf. Artif. Intell. 35(17), 15137\u201315145 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i17.17777","journal-title":"Proceed. AAAI Conf. Artif. Intell."},{"key":"31_CR34","doi-asserted-by":"publisher","unstructured":"Lo, K., Wang, L.L., Neumann, M., Kinney, R., Weld, D.: S2ORC: the semantic scholar open research corpus. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 4969\u20134983. Association for Computational Linguistics, Online (2020). https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.447","DOI":"10.18653\/v1\/2020.acl-main.447"},{"key":"31_CR35","unstructured":"Lopez, P.: GROBID (2008). https:\/\/github.com\/kermitt2\/grobid"},{"key":"31_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1007\/978-3-642-04346-8_62","volume-title":"Research and Advanced Technology for Digital Libraries","author":"P Lopez","year":"2009","unstructured":"Lopez, P.: GROBID: combining automatic bibliographic data recognition and term extraction for scholarship publications. In: Agosti, M., Borbinha, J., Kapidakis, S., Papatheodorou, C., Tsakonas, G. (eds.) ECDL 2009. LNCS, vol. 5714, pp. 473\u2013474. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-04346-8_62"},{"key":"31_CR37","doi-asserted-by":"publisher","unstructured":"Mao, S., Kim, J., Thoma, G.R.: a dynamic feature generation system for automated metadata extraction in preservation of digital materials. In: 1st International Workshop on Document Image Analysis for Libraries, pp. 225\u2013232. IEEE Computer Society, Palo Alto, CA, USA (2004). https:\/\/doi.org\/10.1109\/DIAL.2004.1263251","DOI":"10.1109\/DIAL.2004.1263251"},{"key":"31_CR38","doi-asserted-by":"publisher","unstructured":"Mao, S., Rosenfeld, A., Kanungo, T.: Document structure analysis algorithms: a literature survey. In: Proceedings Document Recognition and Retrieval X. SPIE Proceedings, vol. 5010, pp. 197\u2013207. SPIE, Santa Clara, California, USA (2003). https:\/\/doi.org\/10.1117\/12.476326","DOI":"10.1117\/12.476326"},{"issue":"2","key":"31_CR39","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1023\/A:1009953814988","volume":"3","author":"AK McCallum","year":"2000","unstructured":"McCallum, A.K., Nigam, K., Rennie, J., Seymore, K.: Automating the construction of internet portals with machine learning. Inf. Retrieval 3(2), 127\u2013163 (2000). https:\/\/doi.org\/10.1023\/A:1009953814988","journal-title":"Inf. Retrieval"},{"key":"31_CR40","unstructured":"National Library of Medicine: PubMed. https:\/\/pubmed.ncbi.nlm.nih.gov\/"},{"key":"31_CR41","unstructured":"National Library of Medicine: PubMed Central. https:\/\/www.ncbi.nlm.nih.gov\/pmc\/"},{"issue":"9","key":"31_CR42","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). https:\/\/doi.org\/10.1016\/j.ins.2011.01.014","journal-title":"Inf. Sci."},{"key":"31_CR43","doi-asserted-by":"publisher","unstructured":"Ororbia, A.G., Wu, J., Khabsa, M., WIlliams, K., Giles, C.L.: Big scholarly data in CiteSeerX: information extraction from the web. In: Proceedings of the 24th International Conference on World Wide Web, pp. 597\u2013602. WWW 2015 Companion, Association for Computing Machinery, New York, NY, USA (2015). https:\/\/doi.org\/10.1145\/2740908.2741736","DOI":"10.1145\/2740908.2741736"},{"key":"31_CR44","doi-asserted-by":"publisher","unstructured":"Palmero, G., Dimitriadis, Y.: Structured document labeling and rule extraction using a new recurrent fuzzy-neural system. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition, pp. 181\u2013184. Springer (1999). https:\/\/doi.org\/10.1109\/ICDAR.1999.791754","DOI":"10.1109\/ICDAR.1999.791754"},{"key":"31_CR45","unstructured":"Peng, F., McCallum, A.: Accurate information extraction from research papers using conditional random fields. In: Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics: HLT-NAACL, pp. 329\u2013336. Association for Computational Linguistics, Boston, Massachusetts, USA (2004). https:\/\/aclanthology.org\/N04-1042"},{"issue":"4","key":"31_CR46","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). https:\/\/doi.org\/10.1007\/s00799-018-0242-1","journal-title":"Int. J. Digit. Libr."},{"key":"31_CR47","doi-asserted-by":"publisher","first-page":"217231","DOI":"10.1109\/ACCESS.2020.3042455","volume":"8","author":"STR Rizvi","year":"2020","unstructured":"Rizvi, S.T.R., Dengel, A., Ahmed, S.: A hybrid approach and unified framework for bibliographic reference extraction. IEEE Access 8, 217231\u2013217245 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3042455","journal-title":"IEEE Access"},{"key":"31_CR48","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3389\/frma.2018.00021","volume":"3","author":"D Rodrigues Alves","year":"2018","unstructured":"Rodrigues Alves, D., Colavizza, G., Kaplan, F.: Deep reference mining from scholarly literature in the arts and humanities. Front. Res. Metr. Anal. 3, 21 (2018). https:\/\/doi.org\/10.3389\/frma.2018.00021","journal-title":"Front. Res. Metr. Anal."},{"key":"31_CR49","unstructured":"Saier, T., F\u00e4rber, M.: Bibliometric-enhanced arXiv: a data set for paper-based and citation-based tasks. In: Proceedings of the 8th International Workshop on Bibliometric-enhanced Information Retrieval (BIR). CEUR Workshop Proceedings, vol. 2345, pp. 14\u201326. CEUR-WS.org, Cologne, Germany (2019). http:\/\/ceur-ws.org\/Vol-2345\/paper2.pdf"},{"issue":"3","key":"31_CR50","doi-asserted-by":"publisher","first-page":"3085","DOI":"10.1007\/s11192-020-03382-z","volume":"125","author":"T Saier","year":"2020","unstructured":"Saier, T., F\u00e4rber, M.: unarXive: a large scholarly data set with publications\u2019 full-text, annotated in-text citations, and links to metadata. Scientometrics 125(3), 3085\u20133108 (2020). https:\/\/doi.org\/10.1007\/s11192-020-03382-z","journal-title":"Scientometrics"},{"key":"31_CR51","unstructured":"Schloss Dagstuhl - Leibniz Center for Informatics, University of Trier: dblp: Computer Science Bibliography. https:\/\/dblp.org\/"},{"key":"31_CR52","doi-asserted-by":"publisher","unstructured":"Souza, A., Moreira, V., Heuser, C.: ARCTIC: metadata extraction from scientific papers in PDF using two-layer CRF. In: Proceedings of the 2014 ACM Symposium on Document Engineering, pp. 121\u2013130. DocEng 2014, Association for Computing Machinery, New York, NY, USA (2014). https:\/\/doi.org\/10.1145\/2644866.2644872","DOI":"10.1145\/2644866.2644872"},{"key":"31_CR53","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, pp. 99\u2013108. JCDL 2018, Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3197026.3197048","DOI":"10.1145\/3197026.3197048"},{"key":"31_CR54","doi-asserted-by":"publisher","unstructured":"Tkaczyk, D., Szostek, P., Fedoryszak, M., Dendek, P.J., Bolikowski, \u0141.: CERMINE: automatic extraction of structured metadata from scientific literature. Int. J. Doc. Anal. Recogn. (IJDAR) 18(4), 317\u2013335 (2015). https:\/\/doi.org\/10.1007\/s10032-015-0249-8","DOI":"10.1007\/s10032-015-0249-8"},{"key":"31_CR55","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000\u20136010. NIPS2017, Curran Associates Inc., Red Hook, NY, USA (2017). https:\/\/dl.acm.org\/doi\/10.5555\/3295222.3295349"},{"key":"31_CR56","doi-asserted-by":"publisher","unstructured":"Vilnis, L., Belanger, D., Sheldon, D., McCallum, A.: Bethe projections for non-local inference. In: Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, pp. 892\u2013901. UAI2015, AUAI Press, Arlington, Virginia, USA (2015). https:\/\/doi.org\/10.48550\/arXiv.1503.01397","DOI":"10.48550\/arXiv.1503.01397"}],"container-title":["Lecture Notes in Computer Science","Information for a Better World: Normality, Virtuality, Physicality, Inclusivity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-28032-0_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T13:24:37Z","timestamp":1709645077000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-28032-0_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031280313","9783031280320"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-28032-0_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"10 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"iConference","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Information","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 March 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 March 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconference2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ischools.org\/iConference","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ConfTool","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"197","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":"36","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":"46","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":"2","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":"2","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)"}}]}}