Search results

• PICCL: Philosophical Integrator of Computational and Corpus Libraries

  1 resources

  PICCL is a set of workflows for corpus building through OCR, post-correction, modernization of historic language and Natural Language Processing. It combines Tesseract Optical Character Recognition, TICCL functionality and Frog functionality in a single pipeline. Tesseract offers Open Source software for optical character recognition. 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. Frog enriches textual documents with various linguistic annotations.

  Martin Reynaert, Maarten van Gompel, Ko van der Sloot and Antal van den Bosch. 2015. PICCL: Philosophical Integrator of Computational and Corpus Libraries. Proceedings of CLARIN Annual Conference 2015, pp. 75-79. Wrocław, Poland. http://www.nederlab.nl/cms/wp-content/uploads/2015/10/Reynaert_PICCL-Philosophical-Integrator-of-Computational-and-Corpus-Libraries.pdf

  PICCL

  Use "PICCL: Philosophical Integrator of Computational and Corpus Libraries"

• GrNe: Greek-Dutch dictionary

  1 resources

  Online dictionary (ancient) Greek - Dutch for the letter Pi. Search functions include searches for Greek lemmata, search of Greek declined or conjugated word-forms that lead to the correct lemma ('lemmatizer'), searches for Dutch words leading to different Greek lemmata, and etymological searches. The dictionary is linked to Logeion, the international website of Greek dictionaries at the University of Chicago. The developers estimate that a complete version of the dictionary will be finished by the end of 2015 and that it will be published by the end of 2016. A new dictionary ancient Greek – Dutch is currently under construction at Leiden University. The dictionary is being financed through the 2010 Spinoza award of project director Ineke Sluiter. CLARIN funding enabled the digital production of the letter Pi. Currently, the letters beta, gamma, zeta, pi and sigma are available online. The developers estimate that a complete first version of the dictionary will be finished by the end of 2015 and that it will be published by the end of 2016. The corpus that is being covered by this dictionary covers Greek literature from its beginnings (Homer) and consists of ca. 3.680.000 words (tokens); it includes all classical authors from the 5th and 4th centuries BCE, and a selection of later Greek (selection based on the likelihood that the text will be used by our target groups), but all of the New Testament, Lucian and Plutarch. The dictionary will eventually contain ca. 52.500 headwords. It is based on a thorough comparison of state of the art dictionaries, supplemented with the help of the material from the Thesaurus Linguae Graecae. Greek morphology is complicated. In order to use a dictionary effectively, a rather high level of initial language competence is necessary for the user to be able to relate the word-form s/he finds in a text to the correct basic lemma form, where the definition of the word can be found. This digital dictionary however has an added ‘lemmatizer’ function, which enables the user to type in the word as found in the text and to be redirected to the correct lemma. The digital resource enables both Greek-Dutch searches and searches for the possible Greek equivalents of Dutch terms. This also makes it possible to explore the relation of semantic fields in Dutch and Greek. E.g., it is possible to locate all Greek words that have ‘courage’ as part of their definition. Furthermore, the digital resource makes it possible to locate different Greek words with the same etymological roots. And finally, the dictionary is linked to the website of the University of Chicago, where a comparison of all Greek-x dictionaries is supported. Here, one can enter a Greek word and be provided with the equivalents and definitions in all the dictionaries that are linked on this website.

• TiCClops: Text-Induced Corpus Clean-up online processing system

  3 resources

  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.

  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.

  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

• Usage

  3 resources

  The system here allows you to convert your book pages' images into editable text, presented in a particular text format called XML (eXtended Markup Language) of a particular type called Text-Encoding Initiative or TEI XML. This particular format was developed specifically for being able to mark-up or annotate the text you want to work on, i.e. to add all manner of further information to the actual text, e.g. to build a critical edition of it, which is most likely exactly what you want to do with your author's work.

  Betti, A, Reynaert, M and van den Berg, H. 2017. @PhilosTEI: Building Corpora for Philosophers. In: Odijk, J and van Hessen, A. (eds.) CLARIN in the Low Countries, Pp. 379–392. London: Ubiquity Press. DOI: https://doi.org/10.5334/bbi.32. License: CC-BY 4.0