A Method to Lexical Normalisation of Tweets

  1. Pablo Gamallo 1
  2. Marcos Garcia 1
  3. José Ramom Pichel 2
  1. 1 Universidade de Santiago de Compostela
    info

    Universidade de Santiago de Compostela

    Santiago de Compostela, España

    ROR https://ror.org/030eybx10

  2. 2 Imaxin Software
Book:
XXIX Congreso de la Sociedad Española de Procesamiento de Lenguaje Natural: SEPLN 2013
  1. Alberto Díaz Esteban (coord.)
  2. Iñaki Alegria Loinaz (coord.)
  3. Julio Villena Román (coord.)

Publisher: Sociedad Española para el Procesamiento del Lenguaje Natural

ISBN: 978-84-695-8349-4

Year of publication: 2013

Pages: 81-85

Congress: Sociedad Española para el Procesamiento del Lenguaje Natural. Congreso (29. 2013. Madrid)

Type: Conference paper

Abstract

This paper describes a strategy to perform lexical normalisation of out- of-vocabulary (OOV) words in Spanish tweets. To correct any ill-formed OOV, the normalisation system generates in-vocabulary (IV) candidates found in several lexical resources, and selects the best one. Our method generates two types of candidates, primary and secondary IV candidates, which will be ranked in different ways to select the best candidate.