Quick search
Advanced search in
Research outcomes
Field to searchTerm
Add rule
Filters (7)
The following results are related to Digital Humanities and Cultural Heritage. Are you interested to view more results? Visit OpenAIRE - Explore.
Download Results
5 research outcomes, page 1 of 1
  • publication . Conference object . Contribution for newspaper or weekly magazine . Preprint . 2016
    Open Access English
    Authors:
    Rico Sennrich;
    Country: United Kingdom
    Project: EC | SUMMA (688139), EC | QT21 (645452)

    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 . 2016
    Open Access English
    Authors:
    Ahmed Ali; Peter Bell; James Glass; Yacine Messaoui; Hamdy Mubarak; Steve Renals; Yifan Zhang;
    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
  • publication . Conference object . Other literature type . Contribution for newspaper or weekly magazine . Preprint . 2018
    Open Access English
    Authors:
    Rachel Bawden; Rico Sennrich; Alexandra Birch; Barry Haddow;
    Publisher: HAL CCSD
    Countries: France, France, Switzerland, United Kingdom
    Project: EC | HimL (644402), SNSF | Rich Context in Neural Ma... (10521F_169888), EC | TraMOOC (644333), EC | SUMMA (688139), SNSF | Dating structural fabric ... (200020-105212)

    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 . Preprint . Contribution for newspaper or weekly magazine . 2016
    Open Access English
    Authors:
    Ali, Ahmed; Dehak, Najim; Cardinal, Patrick; Khurana, Sameer; Yella, Sree Harsha; Glass, James; Bell, Peter; Renals, Steve;
    Publisher: ISCA
    Country: United Kingdom
    Project: EC | SUMMA (688139)

    In this paper, we investigate different approaches for dialect identification in Arabic broadcast speech. These methods are based on phonetic and lexical features obtained from a speech recognition system, and bottleneck features using the i-vector framework. We studied...

    Add to ORCIDorcid
  • publication . Conference object . Contribution for newspaper or weekly magazine . Preprint . 2017
    Open Access English
    Authors:
    Maria Nadejde; Siva Reddy; Rico Sennrich; Tomasz Dwojak; Marcin Junczys-Dowmunt; Philipp Koehn; Alexandra Birch;
    Country: United Kingdom
    Project: EC | SUMMA (688139)

    Neural machine translation (NMT) models are able to partially learn syntactic information from sequential lexical information. Still, some complex syntactic phenomena such as prepositional phrase attachment are poorly modeled. This work aims to answer two questions: 1) ...

    Add to ORCIDorcid
5 research outcomes, page 1 of 1