Quick search
Advanced search in
Field to searchTerm
Add rule
Filters (4)
Download Results
17 research outcomes, page 1 of 2
  • publication . Conference object . Preprint . 2020
    Open Access
    Authors:
    Andrew Anderson; Jing Su; Rozenn Dahyot; David Gregg;
    Persistent Identifiers
    Publisher: IEEE
    Project: EC | Bonseyes (732204), SFI | ADAPT: Centre for Digital... (13/RC/2106), SFI | Data-centric ultra-low po... (12/IA/1381), SFI | Lero - the Irish Software... (13/RC/2094)

    Comment: The 2019 International Conference on High Performance Computing & Simulation

    Add to ORCIDorcid
  • publication . Conference object . Contribution for newspaper or weekly magazine . Preprint . 2020
    Open Access English
    Authors:
    Rehm, Georg; Marheinecke, Katrin; Hegele, Stefanie; Piperidis, Stelios; Bontcheva, Kalina; Hajic, Jan; Choukri, Khalid; Vasiljevs, Andrejs; Backfried, Gerhard; Prinz, Christoph; ...
    Publisher: HAL CCSD
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106), EC | X5gon (761758), EC | ELG (825627), EC | BDVe (732630), EC | AI4EU (825619)

    Multilingualism is a cultural cornerstone of Europe and firmly anchored in the European treaties including full language equality. However, language barriers impacting business, cross-lingual and cross-cultural communication are still omnipresent. Language Technologies ...

    Add to ORCIDorcid
  • publication . Preprint . Conference object . 2019
    Open Access English
    Authors:
    T. A. Fathima; Vasudevan Nedumpozhimana; Yee Hui Lee; Stefan Winkler; Soumyabrata Dev;
    Persistent Identifiers
    Project: EC | EDGE (713567), SFI | ADAPT: Centre for Digital... (13/RC/2106)

    We analyse the time series of solar irradiance measurements using chaos theory. The False Nearest Neighbour method (FNN), one of the most common methods of chaotic analysis is used for the analysis. One year data from the weather station located at Nanyang Technological...

    Add to ORCIDorcid
  • publication . Preprint . Conference object . 2019
    Open Access English
    Authors:
    T. A. Fathima; Vasudevan Nedumpozhimana; Yee Hui Lee; Stefan Winkler; Soumyabrata Dev;
    Persistent Identifiers
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106), EC | EDGE (713567)

    Solar irradiance is the primary input for all solar energy generation systems. The amount of available solar radiation over time under the local weather conditions helps to decide the optimal location, technology and size of a solar energy project. We study the behaviou...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . 2019
    Open Access
    Authors:
    Matej Ulicny; Vladimir A. Krylov; Rozenn Dahyot;
    Persistent Identifiers
    Publisher: IEEE
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106), EC | EDGE (713567)

    Convolutional neural networks (CNNs) are very popular nowadays for image processing. CNNs allow one to learn optimal filters in a (mostly) supervised machine learning context. However this typically requires abundant labelled training data to estimate the filter paramet...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . 2019
    Open Access
    Authors:
    Alberto Poncelas; Maja Popović; Dimitar Shterionov; Gideon Maillette de Buy Wenniger; Andy Way;
    Persistent Identifiers
    Publisher: Incoma Ltd., Shoumen, Bulgaria
    Project: EC | EDGE (713567), SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is back-translation (Sennrich et al...

    Add to ORCIDorcid
  • publication . Preprint . Conference object . 2019
    Open Access English
    Authors:
    Poncelas, Alberto; Maillette de Buy Wenniger, Gideon; Way, Andy;
    Project: EC | EDGE (713567), SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Comment: Proceedings of The 8th Workshop on Patent and Scientific Literature Translation, 2019, pages 13--23, Dublin

  • publication . Conference object . Preprint . 2019
    Open Access English
    Authors:
    Poncelas, Alberto; Wenniger, Gideon Maillette de Buy; Way, Andy;
    Publisher: Springer
    Project: EC | EDGE (713567), SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Data selection has proven its merit for improving Neural Machine Translation (NMT), when applied to authentic data. But the benefit of using synthetic data in NMT training, produced by the popular back-translation technique, raises the question if data selection could a...

  • publication . Conference object . Preprint . 2019
    Open Access
    Authors:
    Gideon Maillette de Buy Wenniger; Lambert Schomaker; Andy Way;
    Persistent Identifiers
    Publisher: IEEE
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106), EC | EDGE (713567)

    Neural handwriting recognition (NHR) is the recognition of handwritten text with deep learning models, such as multi-dimensional long short-term memory (MDLSTM) re-current neural networks. Models with MDLSTM layers have achieved state-of-the art results on handwritten t...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . 2018
    Open Access English
    Authors:
    Poncelas, Alberto; Wenniger, Gideon Maillette de Buy; Way, Andy;
    Project: EC | EDGE (713567), SFI | ADAPT: Centre for Digital... (13/RC/2106)

    AbstractData selection techniques applied to neural machine trans-lation (NMT) aim to increase the performance of a model byretrieving a subset of sentences for use as training data.One of the possible data selection techniques are trans-ductive learning methods, which ...

17 research outcomes, page 1 of 2