Zamora Martínez, Francisco Julián(Universitat Politècnica de València, 2012-12-07)
El procesamiento del lenguaje natural es un área de aplicación de la inteligencia artificial, en
particular, del reconocimiento de formas que estudia, entre otras cosas, incorporar información
sintáctica (modelo de lenguaje) ...
Zamora Martínez, Francisco Julián; Castro-Bleda, Maria Jose(World Scientific, 2018)
[EN] Neural Network Language Models (NNLMs) are a successful approach to Natural Language Processing tasks, such as Machine Translation. We introduce in this work a Statistical Machine Translation (SMT) system which fully ...
Pastor Pellicer, Joan; Zamora Martínez, Francisco Julián; España Boquera, Salvador; Castro-Bleda, Maria Jose(Springer Verlag (Germany), 2013)
Imbalance datasets impose serious problems in machine learning. For many tasks characterized by imbalanced data, the F-Measure seems more appropiate than the Mean Square Error or other error measures. This paper studies ...
Zamora Martínez, Francisco Julián; España Boquera, Salvador; Castro-Bleda, Maria Jose; Palacios Corella(Public Library of Science, 2018)
[EN] This paper presents a new method to reduce the computational cost when using Neural Networks as Language Models, during recognition, in some particular scenarios. It is based on a Neural Network that considers input ...
Pastor Pellicer, Joan; Castro-Bleda, Maria Jose; España Boquera, Salvador; Zamora-Martinez, Francisco Julián(IOS Press, 2019)
[EN] Recent improvements in deep learning techniques show that deep models can extract more meaningful data directly from raw signals than conventional parametrization techniques, making it possible to avoid specific feature ...
Castro-Bleda, Maria Jose; Vilar Torres, Juan Miguel; España Boquera, Salvador; Llorens, D.; Marzal Varó, Andrés; Prat, F.; Zamora Martínez, Francisco Julián(Institut d'Estudis Medievals de la Universitat Autònoma de Barcelona, 2014)
[EN] Computer assisted transcription tools can speed up the initial process of reading and transcribing texts. At the same time, new annotation tools open new ways of accessing the text in its graphical form. The balance ...
España Boquera, Salvador; Castro-Bleda, Maria Jose; Gorbe Moya, Jorge; Zamora Martínez, Francisco Julián(Institute of Electrical and Electronics Engineers (IEEE), 2011-04)
This paper proposes the use of hybrid Hidden Markov Model (HMM)/Artificial Neural Network (ANN) models for recognizing unconstrained offline handwritten texts. The structural part of the optical models has been modeled ...
Zamora Martínez, Francisco Julián(Universitat Politècnica de València, 2011-10-18)
El Procesado del Lenguaje Natural es un campo muy importante en tareas del
Reconocimiento de Formas. En este trabajo se exponen diferentes modelos de redes
neuronales y su aplicación a tareas de traducción estadística, ...
Zamora Martínez, Francisco Julián; Frinken, V.; España Boquera, Salvador; Castro-Bleda, Maria Jose; Fischer, A.; Bunke, Horst(Elsevier, 2014-04)
[EN] Unconstrained off-line continuous handwritten text recognition is a very challenging task which has been recently addressed by different promising techniques. This work presents our latest contribution to this task, ...
Castro-Bleda, Maria Jose; España Boquera, Salvador; Pastor Pellicer, Joan; ZAMORA MARTÍNEZ, FRANCISCO JULIÁN(Oxford University Press, 2020-11)
[EN] This paper presents the `NoisyOffice¿ database. It consists of images of printed text documents with noise mainly caused by uncleanliness from a generic office, such as coffee stains and footprints on documents or ...