Contextual Handling in Neural Machine Translation: Look Behind, Ahead and on Both Sides
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/76016
Título: | Contextual Handling in Neural Machine Translation: Look Behind, Ahead and on Both Sides |
---|---|
Autor/es: | Agrawal, Ruchit | Turchi, Marco | Negri, Matteo |
Palabras clave: | Machine Translation |
Área/s de conocimiento: | Lenguajes y Sistemas Informáticos |
Fecha de publicación: | 2018 |
Editor: | European Association for Machine Translation |
Cita bibliográfica: | Agrawal, Ruchit; Turchi, Marco; Negri, Matteo. “Contextual Handling in Neural Machine Translation: Look Behind, Ahead and on Both Sides”. 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. 11-20 |
Resumen: | A salient feature of Neural Machine Translation (NMT) is the end-to-end nature of training employed, eschewing the need of separate components to model different linguistic phenomena. Rather, an NMT model learns to translate individual sentences from the labeled data itself. However, traditional NMT methods trained on large parallel corpora with a one-to-one sentence mapping make an implicit assumption of sentence independence. This makes it challenging for current NMT systems to model inter-sentential discourse phenomena. While recent research in this direction mainly leverages a single previous source sentence to model discourse, this paper proposes the incorporation of a context window spanning previous as well as next sentences as source-side context and previously generated output as target-side context, using an effective non-recurrent architecture based on self-attention. Experiments show improvement over non-contextual models as well as contextual methods using only previous context. |
URI: | http://hdl.handle.net/10045/76016 |
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: | EAMT2018 - Proceedings |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
EAMT2018-Proceedings_03.pdf | 1,54 MB | Adobe PDF | Abrir Vista previa | |
Este ítem está licenciado bajo Licencia Creative Commons