Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 7
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Interactive Machine Translation using Hierarchical Translation Model

  • González-Rubio, Jesús
  • Ortiz-Martínez, Daniel
  • Benedí Ruiz, José Miguel
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] Current automatic machine translation systems are not able to generate error-free translations and human intervention is often required to correct their output. Alternatively, an interactive framework that integrates the human knowledge into the translation process has been presented in previous works. Here, we describe a new interactive machine translation approach that is able to work with phrase-based and hierarchical translation models, and integrates error-correction all in a unified statistical framework. In our experiments, our approach outperforms previous interactive translation systems, and achieves estimated effort reductions of as much as 48% relative over a traditional post-edition system., Work supported by the European Union 7 th Framework Program (FP7/2007-2013) under the CasMaCat project (grans agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Representatively Memorable: Sampling the Right Phrase Set to Get the Text Entry Experiment Right

  • Leiva, Luis A.
  • Sanchis-Trilles, Germán
[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 manually curated Englishonly phrase sets or sampling procedures that do not guarantee phrases being memorable. In response to this need, we present a novel sampling method based on two core ideas: a multiple regression model over language-independent features, and the statistical analysis of the corpus from which phrases will be drawn. Our results show that researchers can finally use a method to successfully curate their own stimuli targeting potentially any language or domain. The source code as well as our phrase sets are publicly available., This work is supported by the 7th Framework Program of the European Commision (FP7/2007-13) under grant agreements 287576 (CASMACAT) and 600707 (tranScriptorium)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

LiveThumbs: A Visual Aid for Web Page Revisitation

  • Leiva, Luis A.
  • Traver, V. Javier
  • Castelló, Vicente
[EN] One problem web users often face is that of remembering which previously visited page is likely to contain some particular piece of information they are now interested in. To ease this revisitation task, we propose a novel approach: using ¿live¿ thumbnails, or small video-like animations of a web page. Our approach is grounded on a two-fold notion: (1) live thumbnails should be more informative than their static counterparts, and (2) live thumbnails can help the user disambiguate among perceptually similar pages. We evaluate a proof-of-concept prototype with 13 users. Preliminary results show that our approach has an interesting potential to enhance web page revisitation in a visually compelling way., This work is partially supported by CasMaCat Project 287576 (FP7 ICT-2011.4.2) and Fundaci¿o Caixa-Castell¿o Bancaixa (project P1-1A2010-11)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

The Impact of Visual Contextualization on UI Localization

  • Leiva, Luis A.
  • Alabau, Vicent
[EN] Translating the text in an interface is a challenging task. Besides the jargon and technical terms, many of the strings are often very short, such as those shown in buttons and pull-down menus. Then, as a result of the lack of visual context in the traditional localization process, an important ambiguity problem arises. We study three approaches to solve this problem: using plain gettext (baseline condition), using gettext plus being able to operate the UI, and translating the UI in-place. We found that translators are substantially faster with plain gettext but commit a significantly higher number of errors in comparison to the other approaches. Unexpectedly, the mixed condition was slower and more error-prone than in-place translation. The latter was found to be comparable to plain gettext in terms of time, although some strings passed unnoticed as the UI was operated. Based on our results, we arrive at a set of recommendations to augment localization tools to improve translator's productivity., This work is supported by the 7th Framework Program of the European Commision (FP7/2007-13) under grant agreements 287576 (CASMACAT) and 600707 (tranScriptorium)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Training of On-line Handwriting Text Recognizers with Synthetic Text Generated Using the Kinematic Theory of Rapid Human Movements

  • Martín-Albo Simón, Daniel
  • Plamondon, Réjean
  • Vidal, Enrique|||0000-0003-4579-5196
A method for automatic generation of synthetic handwritten words is presented which is based in the Kinematic Theory and its Sigma-lognormal model. To generate a new synthetic sample, first a real word is modelled using the Sigmalognormal model. Then the Sigma-lognormal parameters are randomly perturbed within a range, introducing human-like variations in the sample. Finally, the velocity function is recalculated taking into account the new parameters. The synthetic words are then used as training data for a Hidden Markov Model based on-line handwritten recognizer. The experimental results confirm the great potential of the Kinematic Theory of rapid human movements applied to writer adaptation., This work was partially supported by the Universitat Politècnica de València under the PMIA-2013 scholarship, the Spanish MEC under FPU scholarship AP2010-0575, the EU’s 7th Framework Programme (FP7/2007-2013) under grant agreement n. 600707 (tranScriptorium) and n. 287576 (CasMaCat) and the Natural Sciences and Engineering Research Council of Canada (NSERC) under grant RGPIN-915.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

Error-proof, High-performance, and Context-aware Gestures for Interactive Text Edition

  • Leiva, Luis A.
  • Alabau, Vicent
  • Vidal, Enrique|||0000-0003-4579-5196
[EN] We present a straightforward solution to incorporate text-editing gestures to mixed-initiative user interfaces (MIUIs). Our approach provides (1) disambiguation from handwritten text, (2) edition context, (3) virtually perfect accuracy, and (4) a trivial implementation. An evaluation study with 32 e-pen users showed that our approach is suitable to production-ready environments. In addition, performance tests on a desktop PC and on a mobile device revealed that gestures are really fast to recognize (0.1 ms on average). Taken together, these results suggest that our approach can help developers to deploy simple but effective, high-performance text-editing gestures, This work is supported by CasMaCat Project 287576 (FP7 ICT-2011.4.2)
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publication Contribución de congreso (ConferenceOutput)

The New THOT Toolkit for Fully-Automatic and Interactive Statistical Machine Translation

  • Ortiz-Martínez, Daniel
  • Casacuberta Nolla, Francisco|||0000-0002-8497-5598
[EN] We present the new THOT toolkit for fullyautomatic and interactive statistical machine translation (SMT). Initial public versions of THOT date back to 2005 and did only include estimation of phrase-based models. By contrast, the new version offers several new features that had not been previously incorporated. The key innovations provided by the toolkit are computeraided translation, including post-editing and interactive SMT, incremental learning and robust generation of alignments at phrase level. In addition to this, the toolkit also provides standard SMT features such as fully-automatic translation, scalable and parallel algorithms for model training, client-server implementation of the translation functionality, etc. The toolkit can be compiled in Unix-like and Windows platforms and it is released under the GNU Lesser General Public License (LGPL)., Work supported by the European Union 7 th Framework Program (FP7/2007-2013) under the CasMaCat project (grant agreement no 287576), by Spanish MICINN under grant TIN2012-31723, and by the Generalitat Valenciana under grant ALMPR (Prometeo/2009/014).