Autores
Cendejas Castro Eduardo Antonio
Barceló Alonso Grettel
Gelbukh Alexander
Sidorov Grigori
Título Hybrid Algorithm for Word-Level Alignment of Parallel Texts
Tipo Congreso
Sub-tipo SCOPUS
Descripción Lecture Notes in Computer Science
Resumen Given a text in two languages, word alignment task consists of identifying in the two variants of the text specific word occurrences that are mutual translations. The majority of existing text alignment systems follow either a linguistic or a statistical approach. We argue for that both approaches are insufficient when used separately, and suggest a flexible algorithm that combines statistical and linguistic techniques.
Observaciones 14th International Conference on Applications of Natural Language to Information Systems, NLDB 2009; Code 83268; ISBN: 3642125492;978-364212549-2
Lugar Sarrebruck
País Alemania
No. de páginas 293-294
Vol. / Cap. 5723
Inicio 2009-06-24
Fin 2009-06-26
ISBN/ISSN 3642125492;978-36421