rogierkraf 2013-11-30+02:00 clarin.eu:cr1:p_1342181139640 CLARIN Netherlands

Resource http://hdl.handle.net/10032/6d9be58990cc19becc6c37fd85996a26 Resource http://ticclops.clarin.inl.nl/ticclops/ Resource http://ticclops.clarin.inl.nl/philostei/ TiCClops unknown http://ticclops.clarin.inl.nl/ticclops/Dutch Language Institutehttp://portal.clarin.nl/node/1914 published 2015-03-25 CLARIN-NL184.021.003NWOhttp://www.clarin.nlJan OdijkNational Coordinator

Utrecht, the Netherlands

j.odijk@uu.nlUiL-OTSUtrecht University20092015NetherlandsNL TICCL (Text Induced Corpus Clean-up) is a system that is designed to search a corpus for all existing variants of (potentially) all words occurring in the corpus. This corpus can be one text, or several, in one or more directories, located on one or more machines. TICCL creates word frequency lists, listing for each word type how often the word occurs in the corpus. These frequencies of the normalized word forms are the sum of the frequencies of the actual word forms found in the corpus. TICCL is a system that is intended to detect and correct typographical errors (misprints) and OCR errors (optical character recognition) in texts. When books or other texts are scanned from paper by a machine, that then turns these scans, i.e. images, into digital text files, errors occur. For instance, the letter combination `in' can be read as `m', and so the word `regeering' is incorrectly reproduced as `regeermg'. TICCL can be used to detect these errors and to suggest a correct form. Text-Induced Corpus Clean-up (TICCL) was developed first as a prototype at the request of the Koninklijke Bibliotheek - The Hague (KB) and reworked into a production tool according to KB specifications (currently at production version 2.0) mainly during the second half of 2008. It is a fully functional environment for processing possibly very large corpora in order to largely remove the undesirable lexical variation in them. It has provisions for various input and output formats, is flexible and robust and has very high recall and acceptable precision. As a spelling variation detection system it is to the developer’s knowledge unique in making principled use of the input text as possible source for target output canonical forms. As such it is far less domain-sensitive than other approaches: the domain is largely covered by the input text collection. TICCL comes in two variants: one with a classic CLAM web application interface, and one with the PhilosTEI interface. written language tool corpus processing orthographic normalisation Enriching Data Linguistics general linguistics orthography yes Dutchnldno yes Englishengno yes Finnishfinno yes Frenchfrano yes Germandeuno yes German (Fraktur)deuno yes Classical Greekgrcno yes Modern Greekellno yes Icelandicislno yes Italianitano yes Latinlatno yes Polishpolno yes Portugueseporno yes Russianrusno yes Spanishspano yes Swedishsweno Online available graphical user interface web application image picture to be OCR-ed and orthographically normalised image/tiff image/vnd.djvu application/pdf UTF8 text text to be orthographically normalised text/plain UTF8 text text to be orthographically normalised FoLiA text/xml UTF8 text lexicon CSV text/csv UTF8 text frequency list CSV text/csv text

text UTF8 results of orthographic normalisation TEI text/xml

text UTF8 input files in one PDF file application/pdf

unknown public http://ticclops.clarin.inl.nl/ticclops/ 0 EUR servicedesk@ivdnt.org Instituut voor de Nederlandse Taal Institute for the Dutch Language http://www.ivdnt.org/ user http://ticclops.uvt.nl/ticclops_manual.v101.pdf eng in proceedings scientific background yes Reynaert, M. (2008). All, and only, the errors: More complete and consistent spelling and OCR-error correction evaluation. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), Marrakech, Morocco. article scientific background yes Reynaert, M. (2010). Character confusion versus focus word-based correction of spelling and ocr variants in corpora. International Journal on Document Analysis and Recognition, pp 1-15, URL http://dx.doi.org/10.1007/s10032-010-0133-5 http://dev.clarin.nl/sites/default/files/TICClops.jpg TiCClops: Text-Induced Corpus Clean-up online processing system CLARIN-NL http://portal.clarin.nl/node/1914 dr. Martin Reynaert reynaert@tilburguniversity.edu Tilburg University dr. Martin Reynaert reynaert@tilburguniversity.edu Tilburg University unknown unknown