No description, website, or topics provided.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.

  • Version: 0.1
  • Licence: GPL v.3
  • Author: Jesús Mager Mager Hois

wixnlp is a collection of tools to work with the indigenous language wixárika (huichol), as well chunk of gram and corpus data of the language. The tools are design as a first NLP approach for wixárika language, and can be used easily from command prompt. This tools are used by an [wixárika - spanish translator] (, developed at UNAM and UAM universities. The tools are written in Python with an GPLv3 Licence, so feel free to hack on the code!


To segment a wixarika word use

$./ word

From an paried translation file name.wixes, can split the file in to independent files name.wix and This files are used by Moses for translation.

File example (corpus.wixes):

'ena ha p+xuawe=aquí hay agua
'ena ha p+yema=aquí está el agua
'ena ha p+kamawe=aquí no hay agua
'ena ha p+kaxuawe=aquí no hay agua
'ena ha p+kayema=aquí no está el agua

To split the file use:

$./tools/ -s corpus

To merge an wix and an es file in to .wixes:

$./tools/ -m corpus

To normalize and tokenize

$./ corpus.wix

And to segment, and anotate a entire file:

$./ corpus.wix
'ena ha p+3 xuawe
'ena ha p+3 ye15 ma
'ena ha p+3 ka4 mawe
'ena ha p+3 ka4 xuawe
'ena ha p+3 ka4 ye15 ma


You are welcome to use the code under the terms for research or commercial purposes, however please acknowledge its use with a citation: Mager Jesus, Barron Carlos and Meza Ivan. "Traductor estadístico wixarika - español usando descomposición morfológica", COMTEL, number 6, September 2016. Here is a BiBTeX entry:

author = "Mager Hois, Jesús Manuel and Barron Romero, Carlos and Meza Ruíz, Ivan Vladimir",
journal = "COMTEL",
number = "6",
title = "Traductor estadístico wixarika - español usando descomposición morfológica",
year = "2016",
month = sep


This work was supported by the Metropolitan Autonomous University (UAM) and the National Autonomous University of Mexico (UNAM), to my mentors Carlos Barron and Ivan Meza. The logo was desgined by Armando Martínez.