Quick search
Advanced search in
Research outcomes
Field to searchTerm
Add rule
Filters (9)
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
Download Results
4 research outcomes, page 1 of 1
  • publication . Article . Preprint . Conference object . Contribution for newspaper or weekly magazine . 2020
    Open Access English
    Authors:
    Biao Zhang; Philip Williams; Ivan Titov; Rico Sennrich;
    Countries: Switzerland, United Kingdom
    Project: EC | ELITR (825460), SNSF | Multi-Task Learning with ... (PP00P1_176727), EC | GoURMET (825299)

    Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that multilingual NMT requires stro...

    Add to ORCIDorcid
  • publication . Conference object . Other literature type . Article . Contribution for newspaper or weekly magazine . Preprint . 2018
    Open Access English
    Authors:
    Rachel Bawden; Rico Sennrich; Alexandra Birch; Barry Haddow;
    Countries: Switzerland, France, United Kingdom
    Project: SNSF | Dating structural fabric ... (200020-105212), EC | TraMOOC (644333), SNSF | Rich Context in Neural Ma... (10521F_169888), EC | SUMMA (688139), EC | HimL (644402)

    For machine translation to tackle discourse phenomena, models must have access to extra-sentential linguistic context. There has been recent interest in modelling context in neural machine translation (NMT), but models have been principally evaluated with standard autom...

    Add to ORCIDorcid
  • publication . Conference object . Article . Contribution for newspaper or weekly magazine . Preprint . 2016
    Open Access English
    Authors:
    Rico Sennrich;
    Publisher: Association for Computational Linguistics (ACL)
    Country: United Kingdom
    Project: EC | QT21 (645452), EC | SUMMA (688139)

    Analysing translation quality in regards to specific linguistic phenomena has historically been difficult and time-consuming. Neural machine translation has the attractive property that it can produce scores for arbitrary translations, and we propose a novel method to a...

    Add to ORCIDorcid
  • publication . Conference object . Preprint . Contribution for newspaper or weekly magazine . Article . 2016
    Open Access English
    Authors:
    Ahmed Ali; Peter Bell; James Glass; Yacine Messaoui; Hamdy Mubarak; Steve Renals; Yifan Zhang;
    Publisher: Institute of Electrical and Electronics Engineers (IEEE)
    Country: United Kingdom
    Project: EC | SUMMA (688139)

    This paper describes the Arabic Multi-Genre Broadcast (MGB-2) Challenge for SLT-2016. Unlike last year's English MGB Challenge, which focused on recognition of diverse TV genres, this year, the challenge has an emphasis on handling the diversity in dialect in Arabic spe...

    Add to ORCIDorcid
4 research outcomes, page 1 of 1