A Deep source-context feature for lexical selection in statistical machine translation
Visualitza/Obre
10.1016/j.patrec.2016.02.014
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/102922
Tipus de documentArticle
Data publicació2016-05-01
EditorElsevier
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
This paper presents a methodology to address lexical disambiguation in a standard phrase-based statistical machine translation system. Similarity among source contexts is used to select appropriate translation units. The information is introduced as a novel feature of the phrase-based model and it is used to select the translation units extracted from the training sentence more similar to the sentence to translate. The similarity is computed through a deep autoencoder representation, which allows to obtain effective low-dimensional embedding of data and statistically significant BLEU score improvements on two different tasks (English-to-Spanish and English-to-Hindi). (C) 2016 Elsevier B.V. All rights reserved.
CitacióGupta, P., Ruiz, M., Rosso, P., Banchs, R. A Deep source-context feature for lexical selection in statistical machine translation. "Pattern recognition letters", 1 Maig 2016, vol. 75, p. 24-29.
ISSN0167-8655
Versió de l'editorhttp://www.sciencedirect.com/science/article/pii/S0167865516000738
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
mt-deep-main-letters-paper.pdf | 358,8Kb | Visualitza/Obre |