Now showing items 1-20 of 130

    • A Client mobile application for Chinese-Spanish statistical machine translation 

      Centelles, Jordi; Ruiz Costa-Jussà, Marta; Banchs Martínez, Rafael Enrique (2014)
      Conference report
      Open Access
      This show and tell paper describes a client mobile application for Chinese-Spanish machine translation. The system combines a standard server-based statistical machine translation (SMT) system, which requires online ...
    • A Deep source-context feature for lexical selection in statistical machine translation 

      Gupta, Parth; Ruiz Costa-Jussà, Marta; Rosso, Paolo; Banchs Martínez, Rafael Enrique (Elsevier, 2016-05-01)
      Article
      Open Access
      This paper presents a methodology to address lexical disambiguation in a standard phrase-based statistical machine translation system. Similarity among source contexts is used to select appropriate translation units. The ...
    • A differentiable BLEU loss. Analysis and first results 

      Casas Manzanares, Noé; Rodríguez Fonollosa, José Adrián; Ruiz Costa-Jussà, Marta (2018)
      Conference report
      Open Access
      In natural language generation tasks, like neural machine translation and image captioning, there is usually a mismatch between the optimized loss and the de facto evaluation criterion, namely token-level maximum likelihood ...
    • A MOOC on approaches to machine translation 

      Ruiz Costa-Jussà, Marta; Formiga, Lluís; Torrillas Tostado, Oriol; Petit Silvestre, Jordi; Rodríguez Fonollosa, José Adrián (2015-12-10)
      Article
      Open Access
      This paper describes the design, development, and analysis of a MOOC entitled “Approaches to Machine Translation: Rule-based, statistical and hybrid”, and provides lessons learned and conclusions to be taken into account ...
    • A neural approach to language variety translation 

      Ruiz Costa-Jussà, Marta; Zampieri, Marcos; Pal, Santanu (Association for Computational Linguistics, 2018)
      Conference lecture
      Restricted access - publisher's policy
      In this paper we present the first neural-based machine translation system trained to translate between standard national varieties of the same language. We take the pair Brazilian - European Portuguese as an example and ...
    • A non-linear semantic mapping technique for cross-language sentence matching 

      Banchs Martínez, Rafael Enrique; Ruiz Costa-Jussà, Marta (2010-08-01)
      Article
      Restricted access - publisher's policy
    • A Richly annotated, multilingual parallel corpus for hybrid machine translation 

      Avramidis, Elefterios; Ruiz Costa-Jussà, Marta; Federmann, Christian; Melero, Maite; Pecina, Pavel; Van Genabith, Josef (European Language Resources Association (ELRA), 2012)
      Conference report
      Open Access
      In recent years, machine translation (MT) research has focused on investigating how hybrid machine translation as well as system combination approachescan bedesigned so that theresulting hybrid translationsshow an improvement ...
    • ACÚSTICA (Examen 2n quadrimestre, 2n parcial) 

      Ruiz Costa-Jussà, Marta; Nogueiras Rodríguez, Albino; Esquerra Llucià, Ignasi (Universitat Politècnica de Catalunya, 2016-06-06)
      Exam
      Restricted access to the UPC academic community
    • AI reflections in 2020 

      Jobin, Anna; Man, Kingson; Damasio, Antonio; Kaissis, Georgios; Braren, Rickmer; Stoyanovich, Julia; Van Bavel, Jay J.; West, Tessa V.; Mittelstadt, Brendt; Eshraghian, Jason; Ruiz Costa-Jussà, Marta; Tzachor, Asaf; Jamjoom, Aimun A. B.; Taddeo, Mariarosaria; Sinibaldi, Edoardo; Hu, Yipeng; Luengo Oroz, Miguel (Springer Nature, 2021-01-19)
      Article
      Open Access
      We invited authors of selected Comments and Perspectives published in Nature Machine Intelligence in the latter half of 2019 and first half of 2020 to describe how their topic has developed, what their thoughts are about ...
    • AMALEU: una representación universal del lenguaje basada en aprendizaje automático 

      Ruiz Costa-Jussà, Marta (2020-09)
      Article
      Open Access
      El objetivo del proyecto AMALEU es aprender una representación común para diferentes idiomas. Se pretende tener una representación común para la lengua oral y una para la lengua escrita. AMALEU, de dos años de duración, ...
    • An analysis of gender bias studies in natural language processing 

      Ruiz Costa-Jussà, Marta (Springer Science and Business Media LLC, 2019-10-14)
      Article
      Open Access
      Artificial intelligence systems copy and amplify existing societal biases, a problem that by now is widely acknowledged and studied. But is current research of gender bias in natural language processing actually moving ...
    • An IR-based strategy for supporting Chinese-Portuguese translation services in off-line model 

      Centelles, Jordi; Ruiz Costa-Jussà, Marta; Banchs Martínez, Rafael Enrique; Gelbukh, Alexander (2014-04-01)
      Article
      Restricted access - publisher's policy
      This paper describes an Information Retrieval engine that is used to support our Chinese-Portuguese machine translation services when no internet connection is available. Our mobile translation app, which is deployed on ...
    • An Ngram-based reordering model 

      Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (Elsevier, 2009-07)
      Article
      Restricted access - publisher's policy
      This paper describes in detail a novel approach to the reordering challenge in statistical machine translation (SMT). This Ngram-based reordering (NbR) approach uses the powerful techniques of SMT systems to generate a ...
    • An overview of the phrase-based statistical machine translation techniques 

      Ruiz Costa-Jussà, Marta (2012-12-01)
      Article
      Restricted access - publisher's policy
    • Attention weights in transformer NMT fail aligning words between sequences but largely explain model predictions 

      Ferrando Monsonís, Javier; Ruiz Costa-Jussà, Marta (Association for Computational Linguistics, 2021)
      Conference lecture
      Open Access
      This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically ...
    • Automatic and human evaluation study of a rule-based and a statistical Catalan-Spanish machine translation systems 

      Ruiz Costa-Jussà, Marta; Farrús Cabeceran, Mireia; Mariño Acebal, José Bernardo; Rodríguez Fonollosa, José Adrián (2011)
      Conference report
      Open Access
      Machine translation systems can be classified into rule-based and corpus-based approaches, in terms of their core technology. Since both paradigms have largely been used during the last years, one of the aims in the ...
    • Automatic evaluation for E-Learning using latent semantic analysis: A use case 

      Farrus, Mireia; Ruiz Costa-Jussà, Marta (2013-03-01)
      Article
      Open Access
      Assessment in education allows for obtaining, organizing, and presenting information about how much and how well the student is learning. The current paper aims at analysing and discussing some of the most state-of-the-art ...
    • Automatic evaluation of continuous assessment tests 

      Farrus, Mireia; Ruiz Costa-Jussà, Marta; Cobo, German; García Solórzano, David; Villarejo Muñóz, Luis; Banchs, Rafael E. (2010-12-01)
      Part of book or chapter of book
      Open Access
    • Automatic normalization of short texts by combining statistical and rule-based techniques 

      Ruiz Costa-Jussà, Marta; Banchs, Rafael E. (2013-03-01)
      Article
      Open Access
      Short texts are typically composed of small number of words, most of which are abbreviations, typos and other kinds of noise. This makes the noise to signal ratio relatively high for this specific category of text. A high ...
    • Automatic Spanish translation of SQuAD dataset for multi-lingual question answering 

      Carrino, Casimiro Pio; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (European Language Resources Association (ELRA), 2020)
      Conference lecture
      Open Access
      Recently, multilingual question answering became a crucial research topic, and it is receiving increased interest in the NLP community.However, the unavailability of large-scale datasets makes it challenging to train ...