Quick search
Advanced search in
Research outcomes
Field to searchTerm
Add rule
Filters (2)
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
Download Results
26 research outcomes, page 1 of 3
  • publication . Conference object . Preprint . 2020
    Open Access English
    Authors:
    Joachim Wagner; James Barry; Jennifer Foster;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics (ACL)
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Comment: Camera ready for ACL 2020

    Add to ORCID
  • publication . Preprint . Conference object . 2020
    Open Access English
    Authors:
    Xabier Soto; Dimitar Shterionov; Alberto Poncelas; Andy Way;
    Persistent Identifiers
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Machine translation (MT) has benefited from using synthetic training data originating from translating monolingual corpora, a technique known as backtranslation. Combining backtranslated data from different sources has led to better results than when using such data in ...

    Add to ORCID
  • publication . Conference object . Preprint . 2019
    Open Access English
    Authors:
    Alberto Poncelas; Andy Way;
    Persistent Identifiers
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Neural Machine Translation (NMT) models tend to achieve best performance when larger sets of parallel sentences are provided for training. For this reason, augmenting the training set with artificially-generated sentence pairs can boost performance. Nonetheless, the per...

    Add to ORCID
  • publication . Preprint . Conference object . 2019
    Open Access English
    Authors:
    James Barry; Joachim Wagner; Jennifer Foster;
    Persistent Identifiers
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Comment: Submitted to the DeepLo workshop at EMNLP

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

    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 ORCID
  • publication . Article . Other literature type . Preprint . 2018
    Open Access English
    Authors:
    Graham, Yvette; Awad, George; Smeaton, Alan;
    Persistent Identifiers
    Publisher: Public Library of Science
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    We present Direct Assessment, a method for manually assessing the quality of automatically-generated captions for video. Evaluating the accuracy of video captions is particularly difficult because for any given video clip there is no definitive ground truth or correct a...

    Add to ORCID
  • publication . Conference object . Preprint . 2018
    Open Access
    Authors:
    Peyman Passban; Qun Liu; Andy Way;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large...

    Add to ORCID
  • publication . Preprint . Part of book or chapter of book . 2018
    Open Access English
    Authors:
    Antonio Toral; Andy Way;
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Comment: Chapter for the forthcoming book "Translation Quality Assessment: From Principles to Practice" (Springer)

    Add to ORCID
  • publication . Conference object . 2017
    Open Access English
    Authors:
    Alfredo Maldonado; Lifeng Han; Erwan Moreau; Ashjan Alsulaimani; Koel Dutta Chowdhury; Carl Vogel; Qun Liu;
    Persistent Identifiers
    Publisher: Association for Computational Linguistics (ACL)
    Project: SFI | ADAPT: Centre for Digital... (13/RC/2106)

    International audience; A description of a system for identifying Verbal Multi-Word Expressions (VMWEs) in running text is presented. The system mainly exploits universal syntactic dependency features through a Conditional Random Fields (CRF) sequence model. The system ...

    Add to ORCID
  • publication . Article . 2016
    Open Access
    Authors:
    Sandipan Dandapat; Andy Way;
    Persistent Identifiers
    Publisher: Instituto Politecnico Nacional/Centro de Investigacion en Computacion
    Project: EC | FALCON (610879), SFI | ADAPT: Centre for Digital... (13/RC/2106)

    Abstract. In this paper, we describe a technique to improve named entity recognition in a resource-poor language (Hindi) by using cross-lingual information. We use an on-line machine translation system and a separate word alignment phase to find the projection of each H...

    Add to ORCID
26 research outcomes, page 1 of 3