Source code for paper: J. A. Cerón-Guzmán and E. León-Guzmán (2016), Lexical Normalization of Spanish Tweets. NLPIT 2016 (WWW'16 Companion). DOI: 10.1145/2872518.2890558.
normalesp is an open-source spell checker for texts written in Spanish, with a focus on tweets, which has been released to public domain in order to enable reproducibility and foster research on the area.
If you use this software in research, please cite:
@inproceedings{Ceron16,
author = {Cer\'{o}n-Guzm\'{a}n, Jhon Adri\'{a}n and Le\'{o}n-Guzm\'{a}n, Elizabeth},
title = {Lexical Normalization of Spanish Tweets},
booktitle = {Proceedings of the 25th International Conference Companion on World Wide Web},
series = {WWW'16 Companion},
year = {2016},
location = {Montr\&\#233;al, Qu\&\#233;bec, Canada},
pages = {605--610},
publisher = {International World Wide Web Conferences Steering Committee},
}
normalesp has been developed in Python 2.7 and on Debian 7 "wheezy". It has been tested on Debian 7 "wheezy", Debian 8 "jessie", and Debian 9 "Stretch". Because of this, normalesp should successfully run on a Linux system.
Please refer to the /docs directory.