Hey all, I just found this free (GPL) morphological analyser for Quechua... it would be a nice project to convert it to HFST (or lttoolbox) so it could be used in Apertium.
http://www.cs.indiana.edu/~gasser/software.html (see 'AntiMorfo') Examples: >>> l3.anal_word('qu', 'achkaraq'); Palabra: achkaraq CG: substantivo, raíz: <achka> español: varios, mucha, numeroso, muchos, demasiado, mucho, gran cantidad, abundante, harto, muchas, cuantioso, bastante CG: substantivo, raíz: <achka> español: varios, mucha, numeroso, muchos, demasiado, mucho, gran cantidad, abundante, harto, muchas, cuantioso, bastante >>> l3.anal_word('qu', 'imankunamanta'); Palabra: imankunamanta CG: substantivo, raíz: <ima> español: algo, e, objeto, cosa, y, también, algún posesor: 3 sing Caso: ablativo >>> l3.anal_word('qu', 'qillqananchikmi'); Palabra: qillqananchikmi CG: futuro nominal, raíz: <qillqa> español: bordar, pintar, dibujar, escribir, graficar, redactar posesor: 1 plur incl Pragmática: validador CG: substantivo, raíz: <qillqana> español: lapicero, lápiz, bolígrafo, pluma, escritorio posesor: 1 plur incl Pragmática: validador CG: futuro nominal, raíz: <qillqa> español: bordar, pintar, dibujar, escribir, graficar, redactar posesor: 1 plur incl Pragmática: validador Seems that it gives glosses in Spanish too, which is cool! $ wc -l *.lex 1782 a.lex 7789 n.lex 15 v0.lex 4809 v.lex Would probably give enough coverage for a basic gisting system. Fran ------------------------------------------------------------------------------ Forrester recently released a report on the Return on Investment (ROI) of Google Apps. They found a 300% ROI, 38%-56% cost savings, and break-even within 7 months. Over 3 million businesses have gone Google with Google Apps: an online email calendar, and document program that's accessible from your browser. Read the Forrester report: http://p.sf.net/sfu/googleapps-sfnew _______________________________________________ Apertium-stuff mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/apertium-stuff
