{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T18:52:39Z","timestamp":1725821559716},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319155623"},{"type":"electronic","value":"9783319155630"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015]]},"DOI":"10.1007\/978-3-319-15563-0_2","type":"book-chapter","created":{"date-parts":[[2015,5,6]],"date-time":"2015-05-06T03:40:55Z","timestamp":1430883655000},"page":"13-26","source":"Crossref","is-referenced-by-count":0,"title":["Data Gathering, Preparation and Enrichment"],"prefix":"10.1007","author":[{"given":"M\u00e1rio","family":"Rodrigues","sequence":"first","affiliation":[]},{"given":"Ant\u00f3nio","family":"Teixeira","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Alu\u00edsio S, Pelizzoni J, Marchi AR, de Oliveira L, Manenti R, Marquiaf\u00e1vel V (2003) An account of the challenge of tagging a reference corpus for brazilian portuguese. In: Computational processing of the Portuguese language. Springer, Berlin, pp 110\u2013117","DOI":"10.1007\/3-540-45011-4_17"},{"key":"2_CR2","unstructured":"Apache Open NLP Development Community (2014) Apache OpenNLP developer documentation. \n                    www.openlp.apache.org"},{"key":"2_CR3","first-page":"161","volume":"12","author":"DE Appelt","year":"1999","unstructured":"Appelt DE (1999) Introduction to information extraction. Artif Intell Commun 12:161\u2013172","journal-title":"Artif Intell Commun"},{"key":"2_CR4","volume-title":"Natural language processing with Python","author":"S Bird","year":"2009","unstructured":"Bird S, Klein E, Loper E (2009) Natural language processing with Python. O\u2019Reilly, Sebastopol"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Brants T (1995) Tagset reduction without information loss. In: Proceedings of the 33rd annual meeting on Association for Computational Linguistics. pp 287\u2013289","DOI":"10.3115\/981658.981698"},{"key":"2_CR6","unstructured":"Chang AX, Manning CD (2014) TOKENS REGEX: defining cascaded regular expressions over tokens. Technical report CSTR 2014\u201302. Department of Computer Science, Stanford University, Stanford"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Chang P, Galley M, Manning CD (2008) Optimizing Chinese word segmentation for machine translation performance. In: Proceedings of the third workshop on statistical machine translation. pp 224\u2013232","DOI":"10.3115\/1626394.1626430"},{"key":"2_CR8","doi-asserted-by":"publisher","DOI":"10.1515\/9783110218329","volume-title":"Syntactic structures","author":"N Chomsky","year":"2002","unstructured":"Chomsky N (2002) Syntactic structures. Walter de Gruyter, New York"},{"key":"2_CR40","unstructured":"Cunningham H, Maynard D, Bontcheva K (2011) Text processing with GATE, Cunningham:2011:TPG:2018860. Gateway Press, Murphys, CA"},{"key":"2_CR9","volume-title":"The text mining handbook: advanced approaches in analyzing unstructured data","author":"R Feldman","year":"2007","unstructured":"Feldman R, Sanger J (2007) The text mining handbook: advanced approaches in analyzing unstructured data. Cambridge University Press, Cambridge"},{"key":"2_CR10","unstructured":"Giesbrecht E, Evert S (2009) Is part-of-speech tagging a solved task? An evaluation of pos taggers for the German Web as Corpus. In: Proceedings of the fifth Web as Corpus workshop. pp 27\u201335"},{"key":"2_CR11","unstructured":"Gim\u00e9nez J, M\u00e0rquez L (2004) SVMTool: a general POS tagger generator based on support vector machines. In: Proceedings of the 4th international conference on Language Resources and Evaluation (LREC\u201904). Lisbon"},{"key":"2_CR12","volume-title":"Handbook of natural language processing","author":"T G\u00fcng\u00f6r","year":"2010","unstructured":"G\u00fcng\u00f6r T (2010) Part-of-speech tagging. In: Indurkhya N, Damerau FJ (eds) Handbook of natural language processing, 2nd edn. CRC\/Taylor and Francis Group, Boca Raton","edition":"2"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hall J, Nilsson J, Nivre J (2010) Single malt or blended? A study in multilingual parser optimization. In: Trends in parsing technology. Springer, Berlin, pp 19\u201333","DOI":"10.1007\/978-90-481-9352-3_2"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hall D, Durrett G, Klein D (2014) Less grammar, more features. In: Proceedings of ACL. Baltimore, pp 228\u2013237","DOI":"10.3115\/v1\/P14-1022"},{"key":"2_CR15","first-page":"19","volume":"20","author":"A Hotho","year":"2005","unstructured":"Hotho A, N\u00fcrnberger A, Paa\u00df G (2005) A brief survey of text mining. LDV Forum 20:19\u201362","journal-title":"LDV Forum"},{"key":"2_CR16","unstructured":"Huang C-R, \u0160imon P, Hsieh S-K, Pr\u00e9vot L (2007) Rethinking Chinese word segmentation: tokenization, character classification, or wordbreak identification. In: Proceedings of the 45th annual meeting of the ACL on interactive poster and demonstration sessions. pp 69\u201372"},{"key":"2_CR17","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1007\/3-540-60925-3_51","volume-title":"Connectionist, statistical and symbolic approaches to learning for natural language processing","author":"SB Huffman","year":"1996","unstructured":"Huffman SB (1996) Learning information extraction patterns from examples. In: Wertmer S, Riloff E, Scheler G (eds) Connectionist, statistical and symbolic approaches to learning for natural language processing. Springer, Berlin, pp 246\u2013260"},{"key":"2_CR18","volume-title":"Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition","author":"D Jurafsky","year":"2008","unstructured":"Jurafsky D, Martin JH (2008) Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition, 2nd edn. Prentice Hall, New York","edition":"2"},{"key":"2_CR19","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1162\/coli.2006.32.4.485","volume":"32","author":"T Kiss","year":"2006","unstructured":"Kiss T, Strunk J (2006) Unsupervised multilingual sentence boundary detection. Comput Linguist 32:485\u2013525","journal-title":"Comput Linguist"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Klein D, Manning CD (2003) Accurate unlexicalized parsing. In: Proceedings of the 41st annual meeting on Association for Computational Linguistics, vol 1. pp 423\u2013430","DOI":"10.3115\/1075096.1075150"},{"key":"2_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1515\/cogl.1997.8.1.1","volume":"8","author":"RW Langacker","year":"1997","unstructured":"Langacker RW (1997) Constituency, dependency, and conceptual grouping. Cogn Linguist 8:1\u201332","journal-title":"Cogn Linguist"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Manning CD (2011) Part-of-speech tagging from 97% to 100%: is it time for some linguistics? In: Gelbukh A (ed) Computational linguistics and intelligent text processing\u201412th international conference CICLing. Lecture notes in computer science. Springer, Berlin, pp 171\u2013189","DOI":"10.1007\/978-3-642-19400-9_14"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Manning CD, Surdeanu M, Bauer J, Finkel J, Bethard SJ, McClosky D (2014) The Stanford CoreNLP natural language processing toolkit. In: Proceedings of 52nd annual meeting of the Association for Computational Linguistics: system demonstrations. pp 55\u201360","DOI":"10.3115\/v1\/P14-5010"},{"key":"2_CR24","unstructured":"Marantz A (1997) No escape from syntax: don\u2019t try morphological analysis in the privacy of your own lexicon. University of Pennsylvania working papers in linguistics 4, p 14"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Martins AFT, Smith NA, Xing EP (2009) Concise integer linear programming formulations for dependency parsing. In: Proceedings of the joint conference of the 47th annual meeting of the ACL and the 4th international joint conference on natural language processing of the AFNLP, vol 1\u2013vol 1. pp 342\u2013350","DOI":"10.3115\/1687878.1687928"},{"key":"2_CR26","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1023\/B:INRT.0000009441.78971.be","volume":"7","author":"P Mcnamee","year":"2004","unstructured":"Mcnamee P, Mayfield J (2004) Character n-gram tokenization for European language text retrieval. Inf Retr 7:73\u201397","journal-title":"Inf Retr"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Monroe W, Green S, Manning CD (2014) Word segmentation of informal Arabic with domain adaptation. In: Proceedings of the 52nd annual meeting of the Association for Computational Linguistics, vol 2 (short papers). ACL, Baltimore, pp 206\u2013211","DOI":"10.3115\/v1\/P14-2034"},{"key":"2_CR28","unstructured":"Nivre J (2005) Dependency grammar and dependency parsing. MSI report 5133. pp 1\u201332"},{"key":"2_CR29","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1017\/S1351324906004505","volume":"13","author":"J Nivre","year":"2007","unstructured":"Nivre J, Hall J, Nilsson J, Chanev A, Eryigit G, K\u00fcbler S, Marinov S, Marsi E (2007) MaltParser: a language-independent system for data-driven dependency parsing. Nat Lang Eng 13:95\u2013135","journal-title":"Nat Lang Eng"},{"key":"2_CR30","first-page":"243","volume-title":"An introduction to language processing with Perl and Prolog","author":"PM Nugues","year":"2006","unstructured":"Nugues PM (2006) Syntactic formalisms. In: Nugues PM (ed) An introduction to language processing with Perl and Prolog. Springer, Berlin, pp 243\u2013275"},{"key":"2_CR31","unstructured":"Padr\u00f3 L, Stanilovsky E (2012) FreeLing 3.0: towards wider multilinguality, In: Proceedings of the Language Resources and Evaluation Conference (LREC 2012). Istanbul, pp 2473\u20132479"},{"key":"2_CR32","first-page":"241","volume":"23","author":"DD Palmer","year":"1997","unstructured":"Palmer DD, Hearst MA (1997) Adaptive multilingual sentence boundary disambiguation. Comput Linguist 23:241\u2013267","journal-title":"Comput Linguist"},{"key":"2_CR33","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/978-3-642-28569-1_2","volume-title":"Multi-source, multilingual information extraction and summarization","author":"J Piskorski","year":"2013","unstructured":"Piskorski J, Yangarber R (2013) Information extraction: past, present and future. In: Poibeau T, Saggion H, Piskorski J, Yangarber R (eds) Multi-source, multilingual information extraction and summarization. Springer, Berlin, pp 23\u201349"},{"key":"2_CR34","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1108\/eb046814","volume":"14","author":"MF Porter","year":"1980","unstructured":"Porter MF (1980) An algorithm for suffix stripping. Program Electron Libr Inf Syst 14:130\u2013137","journal-title":"Program Electron Libr Inf Syst"},{"key":"2_CR35","unstructured":"Reynar JC, Ratnaparkhi A (1997) A maximum entropy approach to identifying sentence boundaries. In: Proceedings of the fifth conference on applied natural language processing, ANLC\u201997. ACL, Stroudsburg, pp 16\u201319"},{"key":"2_CR36","unstructured":"Schmid H (1994) Probabilistic part-of-speech tagging using decision trees. In: Proceedings of the international conference on new methods in language processing. Manchester"},{"key":"2_CR37","volume-title":"El\u00e9ments de syntaxe structurale","author":"L Tesni\u00e8re","year":"1959","unstructured":"Tesni\u00e8re L (1959) El\u00e9ments de syntaxe structurale. Librairie C. Klincksieck, Paris"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Toutanova K, Klein D, Manning CD, Singer Y (2003) Feature-rich part-of-speech tagging with a cyclic dependency network. In: Proceedings of the 2003 conference of the North American chapter of the Association for Computational Linguistics on human language technology, vol 1. pp 173\u2013180","DOI":"10.3115\/1073445.1073478"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Wong DF, Chao LS, Zeng X (2014) iSentenizer-\u03bc: multilingual sentence boundary detection model. ScientificWorldJournal 2014. doi:10.1155\/2014\/196574","DOI":"10.1155\/2014\/196574"}],"container-title":["SpringerBriefs in Electrical and Computer Engineering","Advanced Applications of Natural Language Processing for Performing Information Extraction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-15563-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T19:46:42Z","timestamp":1559159202000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-15563-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015]]},"ISBN":["9783319155623","9783319155630"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-15563-0_2","relation":{},"ISSN":["2191-8112","2191-8120"],"issn-type":[{"type":"print","value":"2191-8112"},{"type":"electronic","value":"2191-8120"}],"subject":[],"published":{"date-parts":[[2015]]}}}