Lexical Normalization of Spanish Tweets with Rule-Based Components and Language Models
This paper presents a system to normalize Spanish tweets, which uses preprocessing rules, a domain-appropriate edit-distance model, and language models to select correction candidates based on context. The system is an improvement on the tool we submitted to the Tweet-Norm 2013 shared task, and resu...
Na minha lista:
| Publicado no: | Procesamiento del Lenguaje Natural |
|---|---|
| Principais autores: | , , |
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
Sociedad Española para el Procesamiento del Lenguaje Natural
2014
|
| Assuntos: | |
| Acesso em linha: | https://www.redalyc.org/articulo.oa?id=515751575005 |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|