What is EXPERT? The EXPloiting Empirical appRoaches to Translation - - PowerPoint PPT Presentation

what is expert
SMART_READER_LITE
LIVE PREVIEW

What is EXPERT? The EXPloiting Empirical appRoaches to Translation - - PowerPoint PPT Presentation

The EXPERT Project achievements and lessons learnt Constantin Orasan Research Group in Computational Linguistics University of Wolverhampton, UK What is EXPERT? The EXPloiting Empirical appRoaches to Translation (EXPERT) project is an FP7


slide-1
SLIDE 1

The EXPERT Project

achievements and lessons learnt

Constantin Orasan Research Group in Computational Linguistics University of Wolverhampton, UK

slide-2
SLIDE 2

What is EXPERT?

§ The EXPloiting Empirical appRoaches to Translation (EXPERT) project is an FP7 Marie Curie Initial Training Network (ITN) § Running between Oct 2012 and Sept 2016 § 9 partners, 4 associate partners, 12 Early Career Researchers registered for PhDs and 4 Experienced Researchers

slide-3
SLIDE 3

EXPERT: Proposes

From the point of view of training

§ the creation of an Initial Training Network to train young researchers on ways to improve current data-driven MT technologies (TM, SMT and EBMT) § support young researchers of the network during the whole research and development cycle, providing guidance, core and complementary training skills and evaluating the resulting technologies § young researchers to become future leaders in this area

From point of view of research

§ improve existing corpus-based MT technologies § create hybrid technologies by exploiting the strengths of the existing technologies and addressing their main limitations § consider the needs of users when proposing new technologies § there is no clear boundary between fully automatic and semi-automatic translation and that they are tools that can help human translators

slide-4
SLIDE 4

Some of the achievements

User perspective

  • Better

understanding of users’ needs

  • More flexible

user interfaces

  • Evaluation

metrics to predict post- editing effort

  • Better

evaluation metrics Data

  • Methods to

compile corpora from the Web

  • Developed

methods to clean translation memories

  • Proposed a

shared task on cleaning of TMs Human in the loop

  • Better quality

estimation methods

  • Proposed

automatic post- editing methods

  • Improve MT

using human feedback Hybrid approaches

  • Incorporation of

semantic information in matching and retrieval from TMs

  • Integration of

deep learning in the translation process

  • Combination of

TM with SMT Community

  • Organised 4
  • pen training

events

  • Organised

numerous workshops, tutorials, summer/winter schools

  • Produced over

120 publications

  • Made resources

available

slide-5
SLIDE 5
  • Involvement of industry is not only a plus, but also a must, for projects that

aim to foster innovation

  • Getting researchers “out of their corner” and exposing them to the realities
  • f the translation industry is always beneficial
  • Researchers can provide “clever” solutions to problems faced by industry

when they get a clear understanding of the industry’s needs

  • ITN projects provide a fantastic forum for collaborative research
  • ITN projects can quickly adjust to the latest research trends: the EXPERT

project has dropped EBMT in favour of NMT.

Lessons learnt

slide-6
SLIDE 6

The EXPERT fellows

http://expert-itn.eu/?q=content/researchers

slide-7
SLIDE 7

The team

Scientists in charge from partner institutions: Juan José Arevalillo, Alessandro Cattelan, Gloria Corpas Pastor, Josef van Genabith, Manuel Herranz, Qun Liu, Khalil Sima'an and Lucia Specia

slide-8
SLIDE 8

The research presented in this paper is supported by the People Programme (Marie Curie Actions) of the European Union’s Framework Programme (FP7/2007-2013) under REA grant agreement no 317471.

Thank you!