@PhilosTEI: Building Corpora for Philosophers. Betti, A., Reynaert, M., & van den Berg, H. In Odijk, J. & van Hessen, A., editors, CLARIN in the Low Countries, pages 371–384. Ubiquity Press, London, 2017. Paper abstract bibtex The step to e-research in philosophy depends on the availability of high quality, easily and freely accessible corpora in a sustainable format composed from multi-language, multi-script books from different historical periods. Corpora matching these needs are at the moment virtually non-existing. Within @PhilosTei, we have addressed this corpus building problem by developing an open source, web-based, user-friendly workflow from textual images to TEI, based on state-of-the-art open source OCR software, to wit Tesseract, and a multi-language version of TICCL, a powerful OCR post-correction tool. We have demonstrated the utility of the tool by applying it to a multilingual, multi-script corpus of important eighteenth to twentieth-century European philosophical texts.
@incollection{betti_philostei_2017,
address = {London},
title = {@{PhilosTEI}: {Building} {Corpora} for {Philosophers}},
url = {http://dx.doi.org/10.5334/bbi.32},
abstract = {The step to e-research in philosophy depends on the availability of high quality, easily and freely accessible corpora in a sustainable format composed from multi-language, multi-script books from different historical periods. Corpora matching these needs are at the moment virtually non-existing. Within @PhilosTei, we have addressed this corpus building problem by developing an open source, web-based, user-friendly workflow from textual images to TEI, based on state-of-the-art open source OCR software, to wit Tesseract, and a multi-language version of TICCL, a powerful OCR post-correction tool. We have demonstrated the utility of the tool by applying it to a multilingual, multi-script corpus of important eighteenth to twentieth-century European philosophical texts.},
booktitle = {{CLARIN} in the {Low} {Countries}},
publisher = {Ubiquity Press},
author = {Betti, Arianna and Reynaert, Martin and van den Berg, Hein},
editor = {Odijk, Jan and van Hessen, Arjan},
year = {2017},
pages = {371--384},
}
Downloads: 0
{"_id":"HYTTF6uaJnMLoBRPr","bibbaseid":"betti-reynaert-vandenberg-philosteibuildingcorporaforphilosophers-2017","downloads":0,"creationDate":"2017-12-29T18:25:23.824Z","title":"@PhilosTEI: Building Corpora for Philosophers","author_short":["Betti, A.","Reynaert, M.","van den Berg, H."],"year":2017,"bibtype":"incollection","biburl":"https://api.zotero.org/groups/2493581/items?key=esJ5YGDX6948PQKQSPOfhZpO&format=bibtex&limit=100","bibdata":{"bibtype":"incollection","type":"incollection","address":"London","title":"@PhilosTEI: Building Corpora for Philosophers","url":"http://dx.doi.org/10.5334/bbi.32","abstract":"The step to e-research in philosophy depends on the availability of high quality, easily and freely accessible corpora in a sustainable format composed from multi-language, multi-script books from different historical periods. Corpora matching these needs are at the moment virtually non-existing. Within @PhilosTei, we have addressed this corpus building problem by developing an open source, web-based, user-friendly workflow from textual images to TEI, based on state-of-the-art open source OCR software, to wit Tesseract, and a multi-language version of TICCL, a powerful OCR post-correction tool. We have demonstrated the utility of the tool by applying it to a multilingual, multi-script corpus of important eighteenth to twentieth-century European philosophical texts.","booktitle":"CLARIN in the Low Countries","publisher":"Ubiquity Press","author":[{"propositions":[],"lastnames":["Betti"],"firstnames":["Arianna"],"suffixes":[]},{"propositions":[],"lastnames":["Reynaert"],"firstnames":["Martin"],"suffixes":[]},{"propositions":["van","den"],"lastnames":["Berg"],"firstnames":["Hein"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Odijk"],"firstnames":["Jan"],"suffixes":[]},{"propositions":["van"],"lastnames":["Hessen"],"firstnames":["Arjan"],"suffixes":[]}],"year":"2017","pages":"371–384","bibtex":"@incollection{betti_philostei_2017,\n\taddress = {London},\n\ttitle = {@{PhilosTEI}: {Building} {Corpora} for {Philosophers}},\n\turl = {http://dx.doi.org/10.5334/bbi.32},\n\tabstract = {The step to e-research in philosophy depends on the availability of high quality, easily and freely accessible corpora in a sustainable format composed from multi-language, multi-script books from different historical periods. Corpora matching these needs are at the moment virtually non-existing. Within @PhilosTei, we have addressed this corpus building problem by developing an open source, web-based, user-friendly workflow from textual images to TEI, based on state-of-the-art open source OCR software, to wit Tesseract, and a multi-language version of TICCL, a powerful OCR post-correction tool. We have demonstrated the utility of the tool by applying it to a multilingual, multi-script corpus of important eighteenth to twentieth-century European philosophical texts.},\n\tbooktitle = {{CLARIN} in the {Low} {Countries}},\n\tpublisher = {Ubiquity Press},\n\tauthor = {Betti, Arianna and Reynaert, Martin and van den Berg, Hein},\n\teditor = {Odijk, Jan and van Hessen, Arjan},\n\tyear = {2017},\n\tpages = {371--384},\n}\n\n","author_short":["Betti, A.","Reynaert, M.","van den Berg, H."],"editor_short":["Odijk, J.","van Hessen, A."],"key":"betti_philostei_2017","id":"betti_philostei_2017","bibbaseid":"betti-reynaert-vandenberg-philosteibuildingcorporaforphilosophers-2017","role":"author","urls":{"Paper":"http://dx.doi.org/10.5334/bbi.32"},"metadata":{"authorlinks":{"van den berg, h":"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fusers%2F1381186%2Fcollections%2FA7CQ4FV8%2Fitems%3Fkey%3DdvEv4VGZrL0POFKzZn9R2lYC%26format%3Dbibtex%26limit%3D100","betti, a":"https://bibbase.org/show?bib=https%3A%2F%2Fapi.zotero.org%2Fgroups%2F214700%2Fitems%3Fkey%3Dbi2Q7duoPuqjf6lgym4TgM83%26format%3Dbibtex%26limit%3D100&group0=year&css=www.axiom.humanities.uva.nl/axiom.css"}},"downloads":0},"search_terms":["philostei","building","corpora","philosophers","betti","reynaert","van den berg"],"keywords":[],"authorIDs":["KSZt8v5i7kh5S28nf","aeqmsSj8anitxzHwC"],"dataSources":["JodcKTt5D4CtcoY2e","YqqB8NWSxm4bnL8ra","ZHdsvgePffKRdgqdo","ATwFjrHEsqA4GDy8B","LgE8jY3vkdf8Hkrjo","TP6aBGJTwBSyPqCdB","9kNXu23ABH7j4wxXZ","zDZS7QvC6khJT2mcu","MzxSQgLp3GvR2xGtR","GYdQLRi8nMpHxCYKf","6MALumtjgawuQXK93","A397sJ2rAeJ9ZRgJe"]}