{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T13:58:34Z","timestamp":1754488714574},"publisher-location":"Berlin, Heidelberg","reference-count":23,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642372469"},{"type":"electronic","value":"9783642372476"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-37247-6_19","type":"book-chapter","created":{"date-parts":[[2013,3,12]],"date-time":"2013-03-12T06:14:18Z","timestamp":1363068858000},"page":"231-244","source":"Crossref","is-referenced-by-count":2,"title":["Machine Learning for High-Quality Tokenization Replicating Variable Tokenization Schemes"],"prefix":"10.1007","author":[{"given":"Murhaf","family":"Fares","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephan","family":"Oepen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"19_CR1","unstructured":"Adolphs, P., Oepen, S., Callmeier, U., Crysmann, B., Flickinger, D., Kiefer, B.: Some fine points of hybrid natural language parsing. In: Proceedings of the 6th International Conference on Language Resources and Evaluation, Marrakech, Morocco (2008)"},{"key":"19_CR2","first-page":"697","volume-title":"Proceedings of the 21st International Conference on Computational Linguistics and the 44th Meeting of the Association for Computational Linguistics","author":"J.R. Curran","year":"2006","unstructured":"Curran, J.R., Clark, S., Vadas, D.: Multi-tagging for lexicalized-grammar parsing. In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Meeting of the Association for Computational Linguistics, pp. 697\u2013704. Association for Computational Linguistics, Sydney (2006)"},{"key":"19_CR3","unstructured":"Dridan, R., Oepen, S.: Tokenization. Returning to a long solved problem. A survey, contrastive experiment, recommendations, and toolkit. In: Proceedings of the 50th Meeting of the Association for Computational Linguistics, Jeju, Republic of Korea, pp. 378\u2013382 (July 2012)"},{"issue":"1","key":"19_CR4","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1017\/S1351324900002370","volume":"6","author":"D. Flickinger","year":"2000","unstructured":"Flickinger, D.: On building a more efficient grammar by exploiting types. Natural Language Engineering\u00a06(1), 15\u201328 (2000)","journal-title":"Natural Language Engineering"},{"key":"19_CR5","unstructured":"Flickinger, D., Zhang, Y., Kordoni, V.: DeepBank: A dynamically annotated treebank of the Wall Street Journal. In: Proceedings of the 11th International Workshop on Treebanks and Linguistic Theories (TLT 2011), Lisbon, Portugal (2012)"},{"key":"19_CR6","first-page":"381","volume-title":"Human Language Technology Conference: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"J. Foster","year":"2010","unstructured":"Foster, J.: \u201ccba to check the spelling\u201d: Investigating parser performance on discussion forum posts. In: Human Language Technology Conference: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pp. 381\u2013384. Association for Computational Linguistics, Los Angeles (2010)"},{"key":"19_CR7","first-page":"725","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing","author":"S. Green","year":"2011","unstructured":"Green, S., de Marneffe, M.C., Bauer, J., Manning, C.D.: Multiword expression identification with tree substitution grammars: A parsing tour de force with french. In: Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp. 725\u2013735. Association for Computational Linguistics, Edinburgh (2011)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Hovy, E., Marcus, M., Palmer, M., Ramshaw, L., Weischedel, R.: Ontonotes. The 90% solution. In: Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, New York City, USA, pp. 57\u201360 (June 2006)","DOI":"10.3115\/1614049.1614064"},{"key":"19_CR9","first-page":"55","volume-title":"Inquiries into Words, Constraints and Contexts","author":"R.M. Kaplan","year":"2005","unstructured":"Kaplan, R.M.: A method for tokenizing text. Festschrift for Kimmo Koskenniemi on his 60th birthday. In: Arppe, A., Carlson, L., Lind\u00e9n, K., Piitulainen, J., Suominen, M., Vainio, M., Westerlund, H., Yli-Jyr\u00e4, A. (eds.) Inquiries into Words, Constraints and Contexts, pp. 55\u201364. CSLI Publications, Stanford (2005)"},{"key":"19_CR10","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1093\/bioinformatics\/btg1023","volume":"19","author":"J.D. Kim","year":"2003","unstructured":"Kim, J.D., Ohta, T., Teteisi, Y., Tsujii, J.: GENIA corpus \u2014 a semantically annotated corpus for bio-textmining. Bioinformatics\u00a019, i180\u2013i182 (2003)","journal-title":"Bioinformatics"},{"key":"19_CR11","unstructured":"Lavergne, T., Capp\u00e9, O., Yvon, F.: Practical very large scale CRFs. In: Proceedings of the 48th Meeting of the Association for Computational Linguistics, Uppsala, Sweden, pp. 504\u2013513 (July 2010)"},{"key":"19_CR12","first-page":"313","volume":"19","author":"M. Marcus","year":"1993","unstructured":"Marcus, M., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpora of English: The Penn Treebank. Computational Linguistics\u00a019, 313\u2013330 (1993)","journal-title":"Computational Linguistics"},{"key":"19_CR13","doi-asserted-by":"crossref","first-page":"75","DOI":"10.2478\/v10108-012-0010-0","volume":"98","author":"J. Mar\u0161\u00edk","year":"2012","unstructured":"Mar\u0161\u00edk, J., Bojar, O.: TrTok: A Fast and Trainable Tokenizer for Natural Languages. Prague Bulletin of Mathematical Linguistics\u00a098, 75\u201385 (2012)","journal-title":"Prague Bulletin of Mathematical Linguistics"},{"issue":"4","key":"19_CR14","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/s11168-004-7430-4","volume":"2","author":"S. Oepen","year":"2004","unstructured":"Oepen, S., Flickinger, D., Toutanova, K., Manning, C.D.: LinGO Redwoods. A rich and dynamic treebank for HPSG. Research on Language and Computation\u00a02(4), 575\u2013596 (2004)","journal-title":"Research on Language and Computation"},{"key":"19_CR15","first-page":"1379","volume-title":"Proceedings of the 23rd International Conference on Computational Linguistics","author":"L. \u00d8vrelid","year":"2010","unstructured":"\u00d8vrelid, L., Velldal, E., Oepen, S.: Syntactic scope resolution in uncertainty analysis. In: Proceedings of the 23rd International Conference on Computational Linguistics, pp. 1379\u20131387. Association for Computational Linguistics, Stroudsburg (2010)"},{"key":"19_CR16","unstructured":"Petrov, S., McDonald, R.: Overview of the 2012 shared task on parsing the web. In: Notes of the First Workshop on Syntactic Analysis of Non-Canonical Language, SANCL (2012)"},{"key":"19_CR17","series-title":"Studies in Contemporary Linguistics","volume-title":"Head-Driven Phrase Structure Grammar","author":"C. Pollard","year":"1994","unstructured":"Pollard, C., Sag, I.A.: Head-Driven Phrase Structure Grammar. Studies in Contemporary Linguistics. Contemporary Linguistics. The University of Chicago Press, Chicago (1994)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Surdeanu, M., Johansson, R., Meyers, A., M\u00e0rquez, L., Nivre, J.: The CoNLL 2008 shared task on joint parsing of syntactic and semantic dependencies. In: Proceedings of the 12th Conference on Natural Language Learning, Manchester, England, pp. 159\u2013177 (2008)","DOI":"10.3115\/1596324.1596352"},{"key":"19_CR19","unstructured":"Tomanek, K., Wermter, J., Hahn, U.: Sentence and token splitting based on conditional random fields. In: Proceedings of the 10th Conference of the Pacific Association for Computational Linguistics, Melbourne, Australia, pp. 49\u201357 (2007)"},{"key":"19_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/11573036_36","volume-title":"Advances in Informatics","author":"Y. Tsuruoka","year":"2005","unstructured":"Tsuruoka, Y., Tateishi, Y., Kim, J.-D., Ohta, T., McNaught, J., Ananiadou, S., Tsujii, J.: Developing a Robust Part-of-Speech Tagger for Biomedical Text. In: Bozanis, P., Houstis, E.N. (eds.) PCI 2005. LNCS, vol.\u00a03746, pp. 382\u2013392. Springer, Heidelberg (2005)"},{"key":"19_CR21","first-page":"1783","volume-title":"Proceedings of the 20th International Joint Conference on Artifical Intelligence","author":"K. Yoshida","year":"2007","unstructured":"Yoshida, K., Tsuruoka, Y., Miyao, Y., Tsujii, J.: Ambiguous part-of-speech tagging for improving accuracy and domain portability of syntactic parsers. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, pp. 1783\u20131788. Morgan Kaufmann Publishers Inc., Hyderabad (2007)"},{"key":"19_CR22","unstructured":"Ytrest\u00f8l, G.: Cuteforce. Deep deterministic HPSG parsing. In: Proceedings of the 12th International Conference on Parsing Technologies, Dublin, Ireland, pp. 186\u2013197 (2011)"},{"key":"19_CR23","unstructured":"Zhang, Y., Krieger, H.U.: Large-scale corpus-driven PCFG approximation of an HPSG. In: Proceedings of the 12th International Conference on Parsing Technologies, Dublin, Ireland, pp. 198\u2013208 (2011)"}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-37247-6_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,19]],"date-time":"2019-05-19T21:26:22Z","timestamp":1558301182000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-37247-6_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642372469","9783642372476"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-37247-6_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}