Quick search
Advanced search in
Field to searchTerm
Add rule
Filters (5)
Download Results
17 research outcomes, page 1 of 2
  • publication . Conference object . Part of book or chapter of book . 2014
    Open Access English
    Authors:
    Mariani, Joseph,; Rehm, Georg; Uszkoreit, Hans;
    Persistent Identifiers
    Publisher: HAL CCSD
    Project: EC | T4ME NET (249119)

    This article provides an overview of the dissemination work carried out in META-NET from 2010 until early 2014; we describe its impact on the regional, national and international level, mainly with regard to politics and the situation of funding for LT topics. This pape...

    Add to ORCIDorcid
  • publication . Conference object . 2012
    English
    Authors:
    Kn��usl, Hanna; Elsweiler, David; Ludwig, Bernd;
    Persistent Identifiers
    Add to ORCIDorcid
  • publication . Preprint . Article . 2019
    Open Access English
    Authors:
    Francesca A. Pearce; Scott T. Kay; David J. Barnes; Richard G. Bower; Matthieu Schaller;
    Persistent Identifiers
    Project: UKRI | DiRAC-2.5 DC - Operations... (ST/R000832/1), UKRI | DiRAC: Memory Intensive 2... (ST/R002371/1), UKRI | DiRAC: Memory Intensive 2... (ST/S002502/1)

    Comment: 21 pages, 14 figures. Accepted for publication by MNRAS

    Add to ORCIDorcid
  • publication . Conference object . Contribution for newspaper or weekly magazine . Preprint . 2019
    Open Access English
    Authors:
    Jindřich Helcl; Jindřich Libovický; Martin Popel;
    Publisher: Association for Computational Linguistics
    Project: EC | Bergamot (825303)

    Comment: WMT19

    Add to ORCIDorcid
  • publication . Contribution for newspaper or weekly magazine . Preprint . Conference object . 2018
    Open Access English
    Authors:
    Jindřich Helcl; Jindřich Libovický;
    Project: EC | QT21 (645452)

    In this paper, we describe our submissions to the WMT17 Multimodal Translation Task. For Task 1 (multimodal translation), our best scoring system is a purely textual neural translation of the source image caption to the target language. The main feature of the system is...

    Add to ORCIDorcid
  • publication . Conference object . 2018
    Open Access English
    Authors:
    Eckart de Castilho, Richard; Dore, Giulia; Margoni, Thomas; Labropoulou, Penny; Gurevych, Iryna;
    Project: EC | OpenMinTeD (654021)

    A significant concern in processing natural language data is the often unclear legal status of the input and output data/resources. In this paper, we investigate this problem by discussing a typical activity in Natural Language Processing: the training of a machine lear...

  • publication . Article . 2016
    Open Access
    Authors:
    Piotr Przybyła; Matthew Shardlow; Sophie Aubin; Robert Bossy; Richard Eckart de Castilho; Stelios Piperidis; John McNaught; Sophia Ananiadou;
    Persistent Identifiers
    Project: UKRI | Enriching Metabolic PATHw... (BB/M006891/1), EC | OpenMinTeD (654021)

    Text mining is a powerful technology for quickly distilling key information from vast quantities of biomedical literature. However, to harness this power the researcher must be well versed in the availability, suitability, adaptability, interoperability and comparative ...

    Add to ORCIDorcid
  • publication . Conference object . Article . 2012
    Open Access English
    Authors:
    Marta Villegas; Nuria Bel; Carlos Gonzalo; Amparo Moreno; Nuria Simelio;
    Publisher: ACL (Association for Computational Linguistics)
    Project: EC | CLARIN (212230)

    Comunicació presentada a: Eighth International Conference on Language Resources and Evaluation, celebrada a Istanbul, Turkey, del 21 al 27 de maig de 2012.

  • publication . Article . 2014
    Open Access English
    Authors:
    Tressy Arts; Yonatan Belinkov; Nizar Habash; Adam Kilgarriff; Vít Suchomel;
    Persistent Identifiers
    Publisher: Elsevier

    AbstractWe present arTenTen, a web-crawled corpus of Arabic, gathered in 2012. arTenTen consists of 5.8-billion words. A chunk of it has been lemmatized and part-of-speech (POS) tagged with the MADA tool and subsequently loaded into Sketch Engine, a leading corpus query...

    Add to ORCIDorcid
  • publication . Conference object . 2016
    Open Access
    Authors:
    Otegi, A.; Aranberri, N.; Branco, A.; Hajič, J.; Neale, S.; Osenova, P.; Pereira, R.; Popel, M.; Silva, J.; Simov, K.; ...
    Project: EC | QTLEAP (610516)

    This work presents parallel corpora automatically annotated with several NLP tools, including lemma and part of-speech tagging, named-entity recognition and classification, named-entity disambiguation, word-sense disambiguation, and coreference. The corpora comprise bot...

    Add to ORCIDorcid
17 research outcomes, page 1 of 2