L'àmbit tecnològic del centre és el processament automàtic del llenguatge, tant en forma oral com escrita, amb l'objectiu d'ajudar a superar les barreres lingüístiques, facilitant la interacció entre persones, entre persones i dispositius, i l'accessibilitat a la informació multilingüe.
Tecnologies de la llengua són aquelles relacionades amb la creació, la gestió i la utilització de tecnologia i de recursos lingüístics (diccionaris, gramàtiques, etc.) per construir sistemes informàtics capaços de comprendre, interpretar i generar les diverses maneres que tenim els humans per comunicar-nos.
En el pla científic, aquesta activitat es basa en disciplines com ara l'aprenentatge automàtic, el processament de la senyal, la lingüística de corpus, l’enginyeria lingüística o el processament del llenguatge natural escrit o parlat. En el pla quotidià, s’inclou en un ventall ampli d’aplicacions cada cop més habituals: cercadors intel·ligents, assistents virtuals, sistemes automàtics d’atenció.

http://futur.upc.edu/VEU

Enviaments recents

  • Prosodic and spectral iVectors for expressive speech synthesis 

    Jauk, Igor; Bonafonte Cávez, Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2016)
    Comunicació de congrés
    Accés obert
    This work presents a study on the suitability of prosodic andacoustic features, with a special focus on i-vectors, in expressivespeech analysis and synthesis. For each utterance of two dif-ferent databases, a laboratory ...
  • Multi-output RNN-LSTM for multiple speaker speech synthesis with a-interpolation model 

    Pascual, Santiago; Bonafonte Cávez, Antonio (Institute of Electrical and Electronics Engineers (IEEE), 2016)
    Text en actes de congrés
    Accés obert
    Deep Learning has been applied successfully to speech processing. In this paper we propose an architecture for speech synthesis using multiple speakers. Some hidden layers are shared by all the speakers, while there is a ...
  • System combination for machine translation for spoken and written language 

    Matusov, Evgeny; Leusch, Gregor; Federico, Marcello; Mariño Acebal, José Bernardo; Ney, Hermann; Bertoldi, Nicola (2008-09-01)
    Article
    Accés restringit per política de l'editorial
    This paper describes a recently developed method for computing a consensus translation from the outputs of multiple machine translation (MT) systems. A possibly new translation hypothesis can be produced as a result of ...
  • Character-based neural machine translation 

    Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (2016)
    Comunicació de congrés
    Accés obert
    Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, ...
  • Out-of-vocabulary word modelling and rejection for keyword spotting 

    Lleida Solano, Eduardo; Mariño, José B.; Salavedra Molí, Josep; Bonafonte Cávez, Antonio; Monte Moreno, Enrique (International Speech Communication Association (ISCA), 1993)
    Text en actes de congrés
    Accés restringit per política de l'editorial
    This paper presents a combination of out-of-vocabulary (OOV) word modeling and rejection techniques in an attempt to accept utterances embedding a keyword and reject utterances with nonkeywords. The goal of this research ...
  • Tradares: A tool for the automatic evaluation of human translation quality within an MOOC environment 

    Betanzos, Miguel; Ruiz Costa-Jussà, Marta; Belanche Muñoz, Luis Antonio (2017-05-13)
    Article
    Accés restringit per política de l'editorial
    In this paper, we introduce TradARES, a tool for the automatic evaluation of human translation quality developed in the context of an OpenEdx MOOC (Massive Open Online Course), setting the foundation for a tool that provides ...
  • Towards human linguistic machine translation evaluation 

    Ruiz Costa-Jussà, Marta; Farrus, Mireia (2013-12-01)
    Article
    Accés obert
    When evaluating machine translation outputs, linguistics is usually taken into account implicitly. Annotators have to decide whether a sentence is better than another or not, using, for example, adequacy and fluency criteria ...
  • How much hybridisation does machine translation need? 

    Ruiz Costa-Jussà, Marta (2015-10-01)
    Article
    Accés obert
    Rule-based and corpus-based machine translation (MT)have coexisted for more than 20 years. Recently, bound-aries between the two paradigms have narrowed andhybrid approaches are gaining interest from bothacademia and ...
  • Description of the Chinese-to-Spanish rule-based machine translation system developed with a hybrid combination of human annotation and statistical techniques 

    Ruiz Costa-Jussà, Marta; Centelles, Jordi (2015-11-01)
    Article
    Accés obert
    Two of the most popular Machine Translation (MT) paradigms are rule based (RBMT) and corpus based, which include the statistical systems (SMT). When scarce parallel corpus is available, RBMT becomes particularly attractive. ...
  • Domain adaptation strategies in statistical machine translation: a brief overview 

    Ruiz Costa-Jussà, Marta (2015-11-01)
    Article
    Accés obert
    Statistical machine translation (SMT) is gaining interest given that it can easily be adapted to any pair of languages. One of the main challenges in SMT is domain adaptation because the performance in translation drops ...

Mostra'n més