[EN] The essential step of surrogating algorithms is phase randomizing the Fourier transform while preserving the original spectrum amplitude before computing the inverse Fourier transform. In this paper, we propose a new ...
[EN] The problem of automatic text classification is an essential part of text analysis. The improvement of text classification can be done at different levels such as a preprocessing step, network
implementation, etc. In ...
Parcheta, Zuzanna(Universitat Politècnica de València, 2016-11-11)
[EN] The present academic work has been developed as the continuation
of the final project degree where the classification of a few gestures
from spanish sign language was done.
This project introduces improvements with ...
Parcheta, Zuzanna(Universitat Politècnica de València, 2015-07-02)
Este trabajo forma parte de un proyecto más amplio que pretende reconocer gestos
correspondientes a la lengua de signos española y traducirlos a voz en tiempo real.
En concreto, se ha diseñado e implementado el módulo ...
Parcheta, Zuzanna; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco(The Association for Computational Linguistics, 2019-08-02)
[EN] The filtering task of noisy parallel corpora in WMT2019 aims to challenge participants to create filtering methods to be useful for training machine translation systems. In this work, we introduce a noisy parallel ...
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 ...