Recent Submissions

  • 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 ...
  • On the locality of attention in direct speech translation 

    Alastruey Lasheras, Belén; Ferrando Monsonís, Javier; Gallego Olsina, Gerard Ion; Ruiz Costa-Jussà, Marta (Association for Computational Linguistics, 2022)
    Conference lecture
    Open Access
    Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long ...
  • Scanflow: A multi-graph framework for machine learning workflow management, supervision, and debugging 

    Bravo Rocca, Gusseppe Jesus; Liu, Peini; Guitart Fernández, Jordi; Dholakia, Ajay; Ellison, David; Falkanger, Jeffrey; Hodak, Miroslav (2022-09-15)
    Article
    Restricted access - publisher's policy
    Machine Learning (ML) is more than just training models, the whole workflow must be considered. Once deployed, a ML model needs to be watched and constantly supervised and debugged to guarantee its validity and robustness ...
  • A federated learning method for real-time emotion state classification from multi-modal streaming 

    Arijit, Nandi; Xhafa Xhafa, Fatos (Elsevier, 2022-08)
    Article
    Restricted access - publisher's policy
    Emotional and physical health are strongly connected and should be taken care of simultaneously to ensure completely healthy persons. A person’s emotional health can be determined by detecting emotional states from various ...
  • Using player's body-orientation to model pass feasibility in soccer 

    Arbués-Sangüesa, Adrià; Fernández de la Rosa, Javier Eduardo; Ballester, Coloma; Haro, Gloria; Martín, Adrián (2020)
    Conference report
    Open Access
    Given a monocular video of a soccer match, this paper presents a computational model to estimate the most feasible pass at any given time. The method leverages offensive player's orientation (plus their location) and ...
  • Large scale prediction of sick leave duration with nonlinear survival analysis algorithms 

    Béjar Alonso, Javier; Pérez Arnal, Raquel Leandra; Vilalta, Armand; Álvarez Napagao, Sergio; García Gasulla, Dario (2022-07-15)
    Article
    Restricted access - publisher's policy
    The management of sick leaves is a critical task that public and private health systems carry out. This enables the good care of sick workers and guarantees a safe return to their jobs. Most health systems enforce regulations ...
  • The TALP-UPC participation in WMT21 news translation task: an mBART-based NMT approach 

    Escolano Peinado, Carlos; Tsiamas, Ioannis; Basta, Christine Raouf Saad; Ferrando Monsonís, Javier; Ruiz Costa-Jussà, Marta; Rodríguez Fonollosa, José Adrián (Association for Computational Linguistics, 2021)
    Conference report
    Open Access
    This paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission ...
  • Heuri: a Scrabble© playing engine using a probability-based heuristic 

    González Romero, Alejandro; Alquézar Mancho, René; Ramírez Flores, Arturo; González Acuña, Francisco; García Olmedo, Ian (2022-02-16)
    Article
    Open Access
    The game of Scrabble has been successfully tackled by two engines: Quackle and Maven. They attain the state-of-the-art in Computer Scrabble. These engines use simulation techniques and precalculated values to achieve ...
  • Bootstrap–CURE: A novel clustering approach for sensor data: an application to 3D printing industry 

    Suman, Shikha; Karna, Ashutosh; Gibert, Karina (2022-02-19)
    Article
    Open Access
    The agenda of Industry 4.0 highlights smart manufacturing by making machines smart enough to make data-driven decisions. Large-scale 3D printers, being one of the important pillars in Industry 4.0, are equipped with smart ...
  • Operational modes detection in industrial gas turbines using an ensemble of clustering methods 

    Bagherzade Ghazvini, Mina; Sànchez-Marrè, Miquel; Bahilo, Edgar; Angulo Bahón, Cecilio (2021-12-01)
    Article
    Open Access
    Operational modes of a process are described by a number of relevant features that are indicative of the state of the process. Hundreds of sensors continuously collect data in industrial systems, which shows how the ...
  • Adaptive optics control with multi-agent model-free reinforcement learning 

    Pou Mulet, Bartomeu; Ferreira, Florian; Quiñones Moreno, Eduardo; Gratadour, Damien; Martín Muñoz, Mario (2022-01-14)
    Article
    Open Access
    We present a novel formulation of closed-loop adaptive optics (AO) control as a multi-agent reinforcement learning (MARL) problem in which the controller is able to learn a non-linear policy and does not need a priori ...
  • Machine-learning-based condition assessment of gas turbine: a review 

    Castro Cros, Martí de; Velasco García, Manel; Angulo Bahón, Cecilio (2021-12-15)
    Article
    Open Access
    Condition monitoring, diagnostics, and prognostics are key factors in today’s competitive industrial sector. Equipment digitalisation has increased the amount of available data throughout the industrial process, and the ...

View more