Gonzalez Rubio, Jesus(Universitat Politècnica de València, 2011-10-18)
The aim of this research is to improve the translation process. On the one hand, the standard loglinear model parameter optimization process, the MERT algorithm, presents high computational costs, so, as an alternative we ...
Esteve, Marcos; Casacuberta Nolla, Francisco; Rosso, Paolo(Sociedad Española para el Procesamiento del Lenguaje Natural, 2020-09)
[ES] La minería de argumentación permite, mediante herramientas software, obtener cuáles son los argumentos que expresan los autores en un determinado texto. En este artículo se pretende realizar un análisis de la argumentación ...
Pérez González de Martos, Alejandro Manuel; Silvestre Cerdà, Joan Albert; Valor Miró, Juan Daniel; Civera Saiz, Jorge; Juan Císcar, Alfonso(Springer, 2015-09-15)
This paper briefly presents the main features of MLLP s Transcription and Translation Platform, which uses state-of-the-art automatic speech recognition and machine translation systems to generate multilingual subtitles ...
[EN] Accessibility to historical documents is mostly limited to scholars. This is due to the language barrier inherent in human language and the linguistic properties of these documents. Given a historical document, ...
Valor Miró, Juan Daniel; Baquero-Arnal, Pau; Civera Saiz, Jorge; Turró Ribalta, Carlos; Juan, Alfons(International Forum of Educational Technology & Society, 2018)
[EN] Massive Open Online Courses (MOOCs) and Open Educational Resources (OER) are rapidly growing, but are not usually offered in multiple languages due to the lack of cost-effective solutions to translate the different ...
Alabau Gonzalvo, Vicente(Universitat Politècnica de València, 2014-01-27)
This thesis presents scientific contributions to the field of multimodal interac-
tive structured prediction (MISP). The aim of MISP is to reduce the human
effort required to supervise an automatic output, in an efficient ...
[EN] Reducing the human effort performed with the use of interactive-predictive neural machine translation (IPNMT) systems is one of the main goals in this sub-field of machine translation (MT). Prior works have focused ...
Marín Buj, Daniel; Ibánez García, Daniel; Parcheta, Zuzanna; Casacuberta Nolla, Francisco(Instituto Superior Técnico (IST) de Lisboa, 2020-11-05)
[EN] In this paper, we present a machine
translation system implemented by the
Translation Centre for the Bodies of the
European Union. The main goal of this
project is to create domain-specific
machine translation engines ...
Alabau, Vicent; Sanchis Navarro, José Alberto; Casacuberta Nolla, Francisco(Elsevier, 2012-12)
[EN] Interactive structured prediction (ISP) is an emerging framework for structured prediction (SP) where the
user and the system collaborate to produce a high quality output. Typically, search algorithms applied
to ISP ...
[EN] One of the most promising approaches to machine translation consists in formulating the problem by
means of a pattern recognition approach. By doing so, there are some tasks in which online adapta-
tion is needed ...
Montalvá Minguet, Kevin(Universitat Politècnica de València, 2017-02-13)
[EN] Machine Translation systems have been used since their inception by professional
translators to speed up and ease their work. Those systems receive professionally edited
translations through their use, which could ...
Iranzo Sánchez, Javier(Universitat Politècnica de València, 2019-10-30)
[ES] La traducción automática (MT) es un área de investigación sobre el desarrollo de sistemas que traducen textos de manera automática. Actualmente, la mayoría de sistemas de MT utilizan redes neuronales en lo que se ...
We present a new technique to estimate the reliability of the words in automatically generated translations. Our approach addresses confidence estimation as a classification problem where a confidence score is to be predicted ...
Gascó Mora, Guillem(Universitat Politècnica de València, 2011-11-21)
In this master thesis we implement a MT decoder that use the main strenghts of syntax and phrase based approaches. The decoder has two parts: a parser that obtains the syntactic tree, and a tree-tostring method to find the ...
Herget, Katrin(Editorial Universitat Politècnica de València, 2021-07-26)
[EN] Advances in machine translation resulted in an increase of both volume and quality of machine-translated texts. However, machine translation still requires humans to post-edit the translation. This paper proposes a ...
García San Vicente, Javier(Universitat Politècnica de València, 2020-10-13)
[ES] En la última década se han producido varios descubrimientos que han cambiado por completo ciertas áreas del aprendizaje automático, como la visión por computador mediante redes neuronales convolucionales, o la generación ...
[EN] Machine translation systems require human revision to obtain high-quality translations. Interactive methods provide an efficient human¿computer collaboration, notably increasing productivity. Recently, new interactive ...
Garcia Martinez, Maria Mercedes(Universitat Politècnica de València, 2013-02-22)
[ES] La Traducción Automática (TA) es cada vez más creciente en la industria de la traducción
que pide traducciones de calidad más rápidamente. A pesar de esto, las traducciones
obtenidas con TA requieren post-edición ...
Domingo Ballester, Miguel(Universitat Politècnica de València, 2022-02-28)
[ES] Los documentos históricos son una parte importante de nuestra herencia cultural. Sin embargo, debido a la barrera idiomática inherente en el lenguaje humano y a las propiedades lingüísticas de estos documentos, su ...
Mirzaeian, Vahid Reza(Universitat Politècnica de València, 2021-11-26)
[EN] Although the field of machine translation has witnessed huge improvements in recent years, its potentials have not been fully exploited in other interdisciplinary areas such as foreign language teaching. The aim of ...