Affiliations: [a] Institute for Natural Language Processing, University of Stuttgart, Germany
| [b] Facultad de Filosofía y Letras, Universidad Nacional Autónoma de México | [c] Instituto de Ingeniería, Universidad Nacional Autónoma de México | [d] Instituto de Investigaciones en Matemáticas Aplicadas y en Sistemas, Universidad Nacional Autónoma de México
Correspondence:
[*]
Corresponding author. Manuel Mager, Institute for Natural Language Processing, University of Stuttgart, Germany. E-mail: [email protected].
Abstract: User generated data in social networks is often not written in its standard form. This kind of text can lead to large dispersion in the datasets and can lead to inconsistent data. Therefore, normalization of such kind of texts is a crucial preprocessing step for common Natural Language Processing tools. In this paper we explore the state-of-the-art of the machine translation approach to normalize text under low-resource conditions. We also propose an auxiliary task for the sequence-to-sequence (seq2seq) neural architecture novel to the text normalization task, that improves the base seq2seq model up to 5%. This increase of performance closes the gap between statistical machine translation approaches and neural ones for low-resource text normalization.
