 |
 |
Thanks, Gabby, this is a worthy topic. A few notes on the CLTK: We have two methods for Latin: http://docs.cltk.org/en/latest/latin.html#lemmatization <http://docs.cltk.org/en/latest/latin.html#lemmatization> and http://docs.cltk.org/en/latest/latin.html#lemmatization-backoff-method <http://docs.cltk.org/en/latest/latin.html#lemmatization-backoff-method> One for Greek: http://docs.cltk.org/en/latest/greek.html#lemmatization <http://docs.cltk.org/en/latest/greek.html#lemmatization> And I cannot help but mention that, as of this morning, we now have a lemmatizer for Old English: http://docs.cltk.org/en/latest/old_english.html#lemmatization <http://docs.cltk.org/en/latest/old_english.html#lemmatization> Regards, Kyle Jan 18, 2019, 5:23 AM by [log in to unmask]: > Dear all, > > This is a bit of a perenniel topic on this list (last discussed in depth three years ago in 2016). There is currently a page in the Digital Classicist wiki at (> https://wiki.digitalclassicist.org/Morphological_parsing_or_lemmatising_Greek_and_Latin <https://wiki.digitalclassicist.org/Morphological_parsing_or_lemmatising_Greek_and_Latin>> ) which I'm sure needs a bit of updating, and might also usefully be split into several pages (cross-referenced). There are also individual pages for Lemlat, Morpheus, CLTK, Collatinus, and perhaps other tools. > > My question today (in addition to an open call to improve the above, add new pages as relevant, etc.) is more specific: > > - What lemmatisation *services* exist for Greek and Latin? The ideal service would be a site or webservice to which one could upload a text-only list of tokens/forms, and be returned a CSV or similar table of each form and zero-to-multiple candidate lemmata. > - Some projects have occasionally offered the service of performing lemmatization on such a list, offline, and sending the results back to the requester. This is presumably not a scalable solution, but it would be useful to know who might be able to make such offers nevertheless. > - A desktop app that was able to perform large-scale lemmatization locally (either from installed libraries or via accessing online data) would also be very useful. I'd like to know about difficulty of (a) installation and (b) operation. > - Scripts or services that require not only installation but a certain amount of familiarity with coding, may be out of reach of many users who need the morphology service (even if good instructions exist). We should know about and list them, though. > > Am I missing any categories or parameters that would be useful to hear about? > > Many thanks, > > Gabby > > > == > Dr Gabriel BODARD > Reader in Digital Classics > > Institute of Classical Studies > University of London > Senate House > Malet Street > London WC1E 7HU > > E: > [log in to unmask] <mailto:[log in to unmask]> > T: +44 (0)20 78628752 > > http://digitalclassicist.org <http://digitalclassicist.org/> > > ######################################################################## > > To unsubscribe from the DIGITALCLASSICIST list, click the following link: > https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=DIGITALCLASSICIST&A=1 <https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=DIGITALCLASSICIST&A=1> > ######################################################################## To unsubscribe from the DIGITALCLASSICIST list, click the following link: https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=DIGITALCLASSICIST&A=1