- -

Listar por autor "Sanchis Trilles, Germán"

RiuNet: Repositorio Institucional de la Universidad Politécnica de Valencia

Listar por autor "Sanchis Trilles, Germán"

Ordenar por:Orden:Resultados:

  • thumb
    Advanced techniques for domain adaptation in Statistical Machine Translation 
    Chinea Ríos, Mara (Universitat Politècnica de València, 2019-03-04)
    [ES] La Traducción Automática Estadística es un sup-campo de la lingüística computacional que investiga como emplear los ordenadores en el proceso de traducción de un texto de un lenguaje humano a otro. La traducción ...
  • thumb
    An Empirical Analysis of Data Selection Techniques in Statistical Machine Translation 
    Chinea Ríos, Mara; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (Sociedad Española para el Procesamiento del Lenguaje Natural (SEPLN), 2015-09)
    [EN] Domain adaptation has recently gained interest in statistical machine translation. One of the adaptation techniques is based in the selection data. Data selection aims to select the best subset of the bilingual ...
  • thumb
    Building task-oriented machine translation systems 
    Sanchis Trilles, Germán (Universitat Politècnica de València, 2012-09-20)
    La principal meta de esta tesis es desarrollar sistemas de traduccion interactiva que presenten mayor sinergia con sus usuarios potenciales. Por ello, el objetivo es hacer los sistemas estado del arte mas ergonomicos, ...
  • thumb
    CASMACAT: An open source workbench for advanced computer aided translation 
    Alabau, Vicent; Bonkb, Ragnar; Buck, Christian; Carlb, Michael; Casacuberta Nolla, Francisco; García-Martínez, Mercedes; Gonzalez Rubio, Jesus; Koehn, Philipp; Leiva Torres, Luis Alberto; Mesa-Lao, Bartolomé; Ortiz Martínez, Daniel; Saint-Amand, Herve; Sanchis Trilles, Germán; Tsoukalac, Chara (De Gruyter Open, 2013-10)
    [EN] We describe an open source workbench that offers advanced computer aided translation (CAT) functionality: post-editing machine translation (MT), interactive translation prediction (ITP), visualization of word alignment, ...
  • thumb
    Combining Embeddings of Input Data for Text Classification 
    Parcheta, Zuzanna; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco; Rendahl, Robin (Springer-Verlag, 2021-10)
    [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 ...
  • thumb
    Discriminative ridge regression algorithm for adaptation in statistical machine translation 
    Chinea-Ríos, Mara; Sanchis-Trilles, Germán; Casacuberta Nolla, Francisco (Springer-Verlag, 2019-11)
    [EN] We present a simple and reliable method for estimating the log-linear weights of a state-of-the-art machine translation system, which takes advantage of the method known as discriminative ridge regression (DRR). Since ...
  • Icon
    Disseny i desenvolupament d'un programari lliure per a la productització de models d'aprenentatge automàtic mitjançant imatges Docker 
    Millán Soler, Carlos (Universitat Politècnica de València, 2023-09-20)
    [CA] Con el auge del aprendizaje automático, se ha hecho evidente la necesidad de un control riguroso de los modelos entrenados a lo largo de todo su ciclo de vida. Esto ha dado lugar al desarrollo del MlOps, una aplicación ...
  • thumb
    Does more data always yield better translations? 
    Gascó Mora, Guillem; Rocha Sánchez, Martha Alicia; Sanchis Trilles, Germán; Andrés Ferrer, Jesús; Casacuberta Nolla, Francisco (Association for Computational Linguistics, 2012-04-23)
    Nowadays, there are large amounts of data available to train statistical machine translation systems. However, it is not clear whether all the training data actually help or not. A system trained on a subset of such huge ...
  • thumb
    Domain adaptation problem in statistical machine translation systems 
    Chinea Ríos, Mara; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (IOS Press, 2015)
    Globalization suddenly brings many people from different country to interact with each other, requiring them to be able to speak several languages. Human translators are slow and expensive, we find the necessity of developing ...
  • thumb
    Estrategias de aprendizaje online de los pesos del modelo log-lineal en traducción automática interactiva 
    Chinea Ríos, Mara (Universitat Politècnica de València, 2014-03-14)
    [ES] La intervención de los traductores humanos en un escenario de post-edición para corregir las traducciones obtenidas a partir de los sistemas de traducción automática es aún muy necesaria para lograr la calidad ...
  • thumb
    Filtering of Noisy Parallel Corpora Based on Hypothesis Generation 
    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 ...
  • thumb
    Improving translation quality stability using Bayesian predictive adaptation 
    Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (Elsevier, 2015-11)
    [EN] We introduce a Bayesian approach for the adaptation of the log-linear weights present in state-of-the-art statistical machine translation systems. Typically, these weights are estimated by optimising a given translation ...
  • thumb
    Interactive translation prediction versus conventional post-editing in practice: a study with the CasMaCat workbench 
    Sanchis Trilles, Germán; Alabau, Vicent; Buck, Christian; Carl, Michael; Casacuberta Nolla, Francisco; Garcia Martinez, Maria Mercedes; Germann, Ulrich; González Rubio, Jesús; Hill, Robin L.; Kohen, Philipp; Leiva Torres, Luis Alberto; Mesa Lao, Bartolomé; Ortiz Martínez, Daniel; Saint-Amand, Herve; Tsoukala, Chara; Vidal, Enrique (Springer Verlag (Germany), 2014-12)
    [EN] We conducted a field trial in computer-assisted professional translation to compare interactive translation prediction (ITP) against conventional post-editing (PE) of machine translation (MT) output. In contrast to ...
  • thumb
    Log-Linear Weight Optimization Using Discriminative Ridge Regression Method in Statistical Machine Translation 
    Chinea-Ríos, Mara; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (Springer-Verlag, 2017)
    [EN] We present a simple and reliable method for estimating the log-linear weights of a state-of-the-art machine translation system, which takes advantage of the method known as discriminative ridge regression (DRR). Since ...
  • thumb
    Online adaptation strategies for statistical machine translation in post-editing scenarios 
    Martínez Gómez, Pascual; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (Elsevier, 2012-09)
    [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 ...
  • thumb
    Online learning via dynamic reranking for Computer Assisted Translation 
    Martínez Gómez, Pascual; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (Springer Verlag (Germany), 2011)
    New techniques for online adaptation in computer assisted translation are explored and compared to previously existing approaches. Under the online adaptation paradigm, the translation system needs to adapt itself to ...
  • thumb
    Online learning via dynamic reranking for Computer Assisted Translation 
    Martínez Gómez, Pascual (Universitat Politècnica de València, 2011-09-05)
    New techniques for online adaptation in computer assisted translation are explored and compared to previously existing approaches. Under the online adaptation paradigm, the translation system needs to adapt itself to ...
  • thumb
    Passive-aggressive for on-line learning in statistical machine translation 
    Martínez Gómez, Pascual; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (Springer Verlag (Germany), 2011)
    New variations on the application of the passive-aggressive algorithm to statistical machine translation are developed and compared to previously existing approaches. In online adaptation, the system needs to adapt to ...
  • thumb
    Representatively Memorable: Sampling the Right Phrase Set to Get the Text Entry Experiment Right 
    Leiva, Luis A.; Sanchis-Trilles, Germán (ACM, 2014-05-01)
    [EN] In text entry experiments, memorability is a desired property of the phrases used as stimuli. Unfortunately, to date there is no automated method to achieve this effect. As a result, researchers have to use either ...
  • thumb
    Sentence clustering using continuous vector space representation 
    Chinea Ríos, Mara; Sanchis Trilles, Germán; Casacuberta Nolla, Francisco (Springer International Publishing, 2015-06-09)
    In this paper, we present a clustering approach based on the combined use of a continuous vector space representation of sentences and the k-means algorithm. The principal motivation of this proposal is to split a big ...