Compositional Source Word Representations for Neural Machine Translation

Por favor, use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10045/76018
Información del item - Informació de l'item - Item information
Título: Compositional Source Word Representations for Neural Machine Translation
Autor/es: Ataman, Duygu | Di Gangi, Mattia A. | Federico, Marcello
Palabras clave: Machine Translation
Área/s de conocimiento: Lenguajes y Sistemas Informáticos
Fecha de publicación: 2018
Editor: European Association for Machine Translation
Cita bibliográfica: Ataman, Duygu; Di Gangi, Mattia A.; Federico, Marcello. “Compositional Source Word Representations for Neural Machine Translation”. In: Pérez-Ortiz, Juan Antonio, et al. (Eds.). Proceedings of the 21st Annual Conference of the European Association for Machine Translation: 28-30 May 2018, Universitat d'Alacant, Alacant, Spain, pp. 31-40
Resumen: The requirement for neural machine translation (NMT) models to use fixed-size input and output vocabularies plays an important role for their accuracy and generalization capability. The conventional approach to cope with this limitation is performing translation based on a vocabulary of sub-word units that are predicted using statistical word segmentation methods. However, these methods have recently shown to be prone to morphological errors, which lead to inaccurate translations. In this paper, we extend the source-language embedding layer of the NMT model with a bi-directional recurrent neural network that generates compositional representations of the source words from embeddings of character n-grams. Our model consistently outperforms conventional NMT with sub-word units on four translation directions with varying degrees of morphological complexity and data sparseness on the source side.
URI: http://hdl.handle.net/10045/76018
ISBN: 978-84-09-01901-4
Idioma: eng
Tipo: info:eu-repo/semantics/conferenceObject
Derechos: © 2018 The authors. This article is licensed under a Creative Commons 3.0 licence, no derivative works, attribution, CC-BY-ND.
Revisión científica: si
Versión del editor: http://eamt2018.dlsi.ua.es/proceedings-eamt2018.pdf
Aparece en las colecciones:Congresos - EAMT2018 - Proceedings

Archivos en este ítem:
Archivos en este ítem:
Archivo Descripción TamañoFormato 
ThumbnailEAMT2018-Proceedings_05.pdf1,59 MBAdobe PDFAbrir Vista previa


Este ítem está licenciado bajo Licencia Creative Commons Creative Commons