{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T18:58:44Z","timestamp":1780945124594,"version":"3.54.1"},"publisher-location":"Berlin, Heidelberg","reference-count":57,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642309090","type":"print"},{"value":"9783642309106","type":"electronic"}],"license":[{"start":{"date-parts":[[2012,11,11]],"date-time":"2012-11-11T00:00:00Z","timestamp":1352592000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/2.5"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-30910-6_13","type":"book-chapter","created":{"date-parts":[[2013,2,20]],"date-time":"2013-02-20T13:10:41Z","timestamp":1361365841000},"page":"219-247","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":68,"title":["The Construction of a 500-Million-Word Reference Corpus of Contemporary Written Dutch"],"prefix":"10.1007","author":[{"given":"Nelleke","family":"Oostdijk","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Reynaert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V\u00e9ronique","family":"Hoste","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ineke","family":"Schuurman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2012,11,11]]},"reference":[{"key":"13_CR1","volume-title":"The BNC Handbook","author":"G Aston","year":"1998","unstructured":"Aston, G., Burnard, L.: The BNC Handbook. Exploring the British National Corpus with SARA. Edinburgh University Press, Edinburgh (1998)"},{"key":"13_CR2","volume-title":"Evaluation and Validation of the D-Coi Pilot Corpus","author":"A Braasch","year":"2008","unstructured":"Braasch, A., Farse, H., Jongejan, B., Navaretta, C., Olsen, S., Pedersen, B.: Evaluation and Validation of the D-Coi Pilot Corpus. Center for Sprokteknologi, Copenhagen (2008)"},{"issue":"2","key":"13_CR3","first-page":"249","volume":"22","author":"JC Carletta","year":"1996","unstructured":"Carletta, J.C.: Assessing agreement on classification tasks: the kappa statistic. Comput. Linguist. 22 (2), 249\u2013254 (1996)","journal-title":"Comput. Linguist."},{"key":"13_CR4","unstructured":"Chinchor, N., Robinson, P.: MUC-7 Named Entity Task Definition (version 3.5) (1998)"},{"key":"13_CR5","volume-title":"Het Nederlands in de taal-en Spraaktechnologie: prioriteiten Voor Basisvoorzieningen","author":"W Daelemans","year":"2002","unstructured":"Daelemans, W., Strik, H.: Het Nederlands in de taal-en Spraaktechnologie: prioriteiten Voor Basisvoorzieningen. Nederlandse Taalunie, The Hague (2002)"},{"key":"13_CR6","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511486579","volume-title":"Memory-Based Language Processing","author":"W Daelemans","year":"2005","unstructured":"Daelemans, W., van\u00a0den Bosch, A.: Memory-Based Language Processing. Cambridge University Press, Cambridge (2005)"},{"key":"13_CR7","unstructured":"Daelemans, W., Zavrel, J., van\u00a0der Sloot, K., van\u00a0den Bosch, A.: TiMBL: tilburg memory based learner, version 5.1.0, reference guide. Technical Report ILK 04-02, ILK Research Group, Tilburg University (2004)"},{"key":"13_CR8","unstructured":"De\u00a0Clercq, O., Reynaert, M.: SoNaR acquisition manual version 1.0. Technical Report LT3 10-02, LT3 Research Group \u2013 Hogeschool Gent (2010). http:\/\/lt3.hogent.be\/en\/publications\/"},{"key":"13_CR9","unstructured":"De\u00a0Clercq, O., Hoste, V., Hendrickx, I.: Cross-domain Dutch coreference resolution. In: Proceedings of the 8th International Conference on Recent Advances in Natural Language Processing. RANLP 2011, Hissar, Bulgaria (2011)"},{"key":"13_CR10","unstructured":"Desmet, B., Hoste, V.: Named entity recognition through classifier combination. In: Computational Linguistics in the Netherlands 2010: Selected Papers from the Twentieth CLIN Meeting, Utrecht (2010)"},{"key":"13_CR11","unstructured":"Doddington, G., Mitchell, A., Przybocki, M., Ramshaw, R., Strassel, S., Weischedel, R.: The automatic content extraction (ACE) program tasks, data, and evaluation. In: Proceedings of the Fourth International Conference on Language Resources and Evaluation, Lisbon, pp. 837\u2013840. LREC-2004 (2004)"},{"key":"13_CR12","unstructured":"Hendrickx, I., Bouma, G., Coppens, F., Daelemans, W., Hoste, V., Kloosterman, G., Mineur, A.M., Vloet, J.V.D., Verschelde, J.L.: A coreference corpus and resolution system for Dutch. In: Proceedings of the Sixth International Conference on Language Resources and Evaluation, Marrakech, pp. 144\u2013149. LREC-2008 (2008)"},{"key":"13_CR13","unstructured":"Herceg, P.M., Ball, C.N.: A comparative study of PDF generation methods: measuring loss of fidelity when converting Arabic and Persian MS Word files to PDF. Technical Report MTR110043, Mitre (2011). http:\/\/www.mitre.org\/work\/tech_papers\/2011\/11_0753\/11_0753.pdf"},{"key":"13_CR14","unstructured":"Hoekstra, H., Moortgat, M., Renmans, B., Schouppe, M., Schuurman, I., Van\u00a0der Wouden, T.: CGN syntactische annotatie. http:\/\/www.ccl.kuleuven.be\/Papers\/sa-man_DEF.pdf (2004)"},{"key":"13_CR15","unstructured":"Hoste, V.: Optimization issues in machine learning of coreference resolution. Ph.D. thesis, Antwerp University (2005)"},{"key":"13_CR16","unstructured":"Ide, N., Macleod, C., Fillmore, C., Jurafsky, D.: The American national corpus: an outline of the project. In: Proceedings of International Conference on Artificial and Computational Intelligence. ACIDCA-2000, Monastir (2000)"},{"key":"13_CR17","unstructured":"Johnson, C.R., Fillmore, C.J., Petruck, M.R.L., Baker, C.F., Ellsworth, M.J., Ruppenhofer, J., Wood, E.J.: FrameNet: theory and practice. ICSI Technical Report tr-02-009 (2002)"},{"key":"13_CR18","doi-asserted-by":"crossref","unstructured":"Karttunen, L.: Discourse Referents. Syntax and Semantics, vol.\u00a07. Academic, New York (1976)","DOI":"10.1163\/9789004368859_021"},{"key":"13_CR19","unstructured":"Ku\u010dova, L., Haji\u010dova, E.: Coreferential relations in the Prague dependency treebank. In: Proceedings of DAARC 2004, Azores, pp. 97\u2013102 (2004)"},{"issue":"3","key":"13_CR20","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1080\/13658810701626244","volume":"22","author":"J Leveling","year":"2008","unstructured":"Leveling, J., Hartrumpf, S.: On metonymy recognition for geographic information retrieval. Int. J. Geogr. Inf. Sci. 22 (3), 289\u2013299 (2008)","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"13_CR21","unstructured":"Markert, K., Nissim, M.: Towards a corpus annotated for metonymies: the case of location names. In: Proceedings of the Third International Conference on Language Resources and Evaluation, Las Palmas, pp. 1385\u20131392. LREC-2002 (2002)"},{"key":"13_CR22","unstructured":"Martens, S.: Varro: an algorithm and toolkit for regular structure discovery in treebanks. In: Proceedings of Coling 2010, Beijing, pp. 810\u2013818 (2010)"},{"key":"13_CR23","unstructured":"Martens, S.: Quantifying linguistic regularity. Ph.D. thesis, KU Leuven (2011)"},{"key":"13_CR24","doi-asserted-by":"crossref","unstructured":"Monachesi, P., Stevens, G., Trapman, J.: Adding semantic role annotation to a corpus of written Dutch. In: Proceedings of the Linguistic Annotation Workshop (Held in Conjunction with ACL 2007), Prague (2007)","DOI":"10.3115\/1642059.1642072"},{"key":"13_CR25","unstructured":"Oostdijk, N.: The spoken dutch corpus. Outline and first evaluation. In: Proceedings of the Second International Conference on Language Resources and Evaluation, Athens, pp. 887\u2013894. LREC-2000 (2000)"},{"key":"13_CR26","unstructured":"Oostdijk, N.: Dutch language corpus initiative, pilot corpus. Corpus description. TR-D-COI-06-09 (2006)"},{"key":"13_CR27","unstructured":"Oostdijk, N.: A reference corpus of written Dutch. Corpus design. TR-D-COI-06f (2006)"},{"key":"13_CR28","unstructured":"Oostdijk, N., Boves, L.: User requirements analysis for the design of a reference corpus of written Dutch. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, Genoa, pp. 1206\u20131211. LREC-2006 (2006)"},{"key":"13_CR29","doi-asserted-by":"crossref","unstructured":"Palmer, M., Gildea, D., Kingsbury, P.: The proposition bank: a corpus annotated with semantic roles. Comput. Linguist. J. 31 (1) (2005)","DOI":"10.1162\/0891201053630264"},{"key":"13_CR30","unstructured":"Poesio, M., Artstein, R.: Anaphoric annotation in the ARRAU corpus. In: Proceedings of the Sixth International Conference on Language Resources and Evaluation, Marrakech, pp. 1170\u20131174. LREC-2008 (2008)"},{"issue":"4","key":"13_CR31","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1007\/s10579-009-9108-x","volume":"44","author":"M Recasens","year":"2010","unstructured":"Recasens, M., Marti, M.A.: AnCora-CO: coreferentially annotated corpora for Spanish and Catalan. Lang. Resour. Eval. 44 (4), 315\u2013345 (2010)","journal-title":"Lang. Resour. Eval."},{"key":"13_CR32","unstructured":"Reynaert, M.: Corpus-induced corpus cleanup. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, LREC-2006, Trento, pp. 87\u201392 (2006)"},{"key":"13_CR33","first-page":"617","volume-title":"Proceedings of the Computational Linguistics and Intelligent Text Processing 9th International Conference, CICLing 2008","author":"M Reynaert","year":"2008","unstructured":"Reynaert, M.: Non-interactive OCR post-correction for giga-scale digitization projects. In: Gelbukh, A. (ed.) Proceedings of the Computational Linguistics and Intelligent Text Processing 9th International Conference, CICLing 2008, vol.\u00a04919, pp. 617\u2013630. Springer, Berlin (2008)"},{"issue":"2","key":"13_CR34","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s10032-010-0133-5","volume":"14","author":"Martin W. C. Reynaert","year":"2010","unstructured":"Reynaert, M.: Character confusion versus focus word-based correction of spelling and OCR variants in corpora. Int. J. Doc. Anal. Recognit. 1\u201315 (2010). http:\/\/dx.doi.org\/10.1007\/s10032-010-0133-5 , doi:10.1007\/s10032-010-0133-5","journal-title":"International Journal on Document Analysis and Recognition (IJDAR)"},{"key":"13_CR35","unstructured":"Sanders, E.: Collecting and analysing chats and tweets in SoNaR. In: Proceedings of the Eighth International Conference of Language Resources and Evaluation, Istanbul, pp.\u00a02253\u20132256. LREC-2012 (2012)"},{"key":"13_CR36","unstructured":"Sauri, R., Littman, J., Knippen, B., Gaizauskas, R., Setzer, A., Pustejovsky, J.: TimeML annotation guidelines, version 1.2.1. http:\/\/timeml.org\/site\/publications\/specs.html (2006)"},{"key":"13_CR37","unstructured":"Schuurman, I.: Spatiotemporal annotation on top of an existing treebank. In: De Smedt, K., Hajic, J., Kuebler, S. (eds.) Proceedings of the Sixth International Workshop on Treebanks and Linguistic Theories, Bergen, pp. 151\u2013162 (2007)"},{"key":"13_CR38","unstructured":"Schuurman, I.: Which New York, which Monday? The role of background knowledge and intended audience in automatic disambiguation of spatiotemporal expressions. In: Proceedings of CLIN 17, Leuven (2007)"},{"key":"13_CR39","unstructured":"Schuurman, I.: Spatiotemporal annotation using MiniSTEx: how to deal with alternative, foreign, vague and obsolete names? In: Proceedings of the Sixth Conference on International Language Resources and Evaluation (LREC\u201908), Marrakech (2008)"},{"key":"13_CR40","unstructured":"Schuurman, I., Vandeghinste, V.: Cultural aspects of spatiotemporal analysis in multilingual applications. In: Proceedings of the Seventh Conference on International Language Resources and Evaluation (LREC\u201910). European Language Resources Association (ELRA), Valletta (2010)"},{"key":"13_CR41","doi-asserted-by":"crossref","unstructured":"Schuurman, I., Vandeghinste, V.: Spatiotemporal annotation: interaction between standards and other formats. In: IEEE-ICSC Workshop on Semantic Annotation for Computational Linguistic Resources, Palo Alto (2011)","DOI":"10.1109\/ICSC.2011.31"},{"key":"13_CR42","unstructured":"Schuurman, I., Schouppe, M., Van\u00a0der Wouden, T., Hoekstra, H.: CGN, an annotated corpus of spoken Dutch. In: Proceedings of the Fourth International Conference on Linguistically Interpreed Corpora, Budapest, pp. 101\u2013112. LINC-2003 (2003)"},{"key":"13_CR43","unstructured":"SpatialML: Annotation Scheme for Marking Spatial Expressions in Natural Language. MITRE (2007). Version 2.0, LDC, Upenn"},{"key":"13_CR44","unstructured":"Steinberger, R., Pouliquen, B., Widiger, A., Ignat, C., Erjavec, T., Tufis, D., Varga, D.: The JRC-Acquis: a multilingual aligned parallel corpus with 20+ languages. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, Genoa, pp. 2142\u20132147. LREC-2006 (2006) http:\/\/arxiv.org\/ftp\/cs\/papers\/0609\/0609058.pdf"},{"key":"13_CR45","doi-asserted-by":"crossref","unstructured":"Tjong Kim\u00a0Sang, E.: Introduction to the CoNLL-2002 shared task: language-independent named entity recognition. In: Proceedings of the 6th Conference on Natural Language Learning, Taipei, pp. 155\u2013158 (2002)","DOI":"10.3115\/1118853.1118877"},{"key":"13_CR46","volume-title":"Manual for semantic annotation in D-Coi","author":"J Trapman","year":"2006","unstructured":"Trapman, J., Monachesi, P.: Manual for semantic annotation in D-Coi. Technical Report, Utrecht University (2006)"},{"key":"13_CR47","unstructured":"Treurniet, M., De\u00a0Clercq, O., Oostdijk, N., Van\u00a0den Heuvel, H.: Collecting a corpus of Dutch SMS. In: Proceedings of the Eighth International Conference of Language Resources and Evaluation, Istanbul, pp. 2268\u20132273. LREC-2012 (2012)"},{"key":"13_CR48","unstructured":"Van\u00a0den Bosch, A., Schuurman, I., Vandeghinste, V.: Transferring PoS-tagging and lemmatisation tools from spoken to written Dutch corpus development. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, Genoa. LREC-2006 (2006)"},{"key":"13_CR49","first-page":"99","volume-title":"Computational Linguistics in the","author":"A Bosch Van den","year":"2007","unstructured":"Van\u00a0den Bosch, A., Busser, B., Canisius, S., Daelemans, W.: An efficient memory-based morphosyntactic tagger and parser for Dutch. In: Dirix, P., Schuurman, I., Vandeghinste, V., Van\u00a0Eynde, F. (eds.) Computational Linguistics in the Netherlands: Selected Papers from the Seventeenth CLIN Meeting, Leuven, pp. 99\u2013114 (2007)"},{"key":"13_CR50","unstructured":"Van\u00a0Eynde, F.: Part of speech tagging en lemmatisering. Protocol voor annotatoren in D-Coi. Centrum voor Computerlingu\u00efstiek, Leuven. http:\/\/www.let.rug.nl\/vannoord\/Lassy\/POS-manual.pdf internal document"},{"key":"13_CR51","unstructured":"van Gompel, M.: Folia: format for linguistic annotation. http:\/\/ilk.uvt.nl\/folia\/folia.pdf (2011)"},{"key":"13_CR52","unstructured":"Van\u00a0Noord, G.: At last parsing is now operational. In: Verbum Ex Machina, Actes De La 13e Conference sur Le Traitement Automatique des Langues Naturelles, Leuven, pp. 20\u201342. TALN-2006 (2006)"},{"key":"13_CR53","unstructured":"Van\u00a0Noord, G., Schuurman, I., Vandeghinste, V.: Syntactic annotation of large corpora in STEVIN. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation, Genoa, pp. 1811\u20131814. LREC-2006 (2006)"},{"key":"13_CR54","volume-title":"Information Retrieval","author":"C Rijsbergen Van","year":"1979","unstructured":"Van\u00a0Rijsbergen, C.: Information Retrieval. Buttersworth, London (1979)"},{"key":"13_CR55","doi-asserted-by":"crossref","unstructured":"Vilain, M., Burger, J., Aberdeen, J., Connolly, D., Hirschman, L.: A model-theoretic coreference scoring scheme. In: Proceedings of the Sixth Message Understanding Conference (MUC-6), Columbia, pp. 45\u201352 (1995)","DOI":"10.3115\/1072399.1072405"},{"key":"13_CR56","unstructured":"Weischedel, R., Pradhan, S., Ramshaw, L., Palmer, M., Xue, N., Marcus, M., Taylor, A., Greenberg, C., Hovy, E., Belvin, R., Houston, A.: OntoNotes Release 3.0. LDC2009T24. Linguistic Data Consortium (2009)"},{"key":"13_CR57","unstructured":"Woordenlijst Nederlandse Taal: SDU Uitgevers, The Hague (1995)"}],"container-title":["Theory and Applications of Natural Language Processing","Essential Speech and Language Technology for Dutch"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-30910-6_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,22]],"date-time":"2020-07-22T15:37:07Z","timestamp":1595432227000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-30910-6_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,11]]},"ISBN":["9783642309090","9783642309106"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-30910-6_13","relation":{},"ISSN":["2192-032X","2192-0338"],"issn-type":[{"value":"2192-032X","type":"print"},{"value":"2192-0338","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,11,11]]},"assertion":[{"value":"11 November 2012","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}