Newsletter 1/2015

Objectives

The HimL project aims to make public health information available in a wider variety of languages. We will do this using fully automatic machine translation, combining the statistical paradigm with deep linguistic techniques. This MT will be integrated into the live systems run by NHS 24 and Cochrane.

To be effective, our machine translation will need to address three important problems.

  • The translation system should be adapted to the domain.
  • It should produce an accurate rendering of the original, avoiding blatant semantic errors such as misuse of negation.
  • It should support morphologically rich languages, such as those found in central and eastern Europe.

Basics about project:

  • The project is supported by the EU under the Horizon 2020 programme, and coordinated by Barry Haddow, University of Edinburgh, Scotland.
  • The partners are University of Edinburgh, Charles University, Prague, Ludwig Maximilian University of Munich, NHS 24, Cochrane and Lingea.
  • The project runs from February 1st, 2015 to January 31st, 2018.
  • The first meeting of partners was conducted in Edinburgh, on 3-4th February 2015.

More:

To an ever-increasing extent, web-based services are providing a frontline for healthcare information in Europe. They help citizens find answers to their questions and help them understand and find the local services they need. However, due to the number of languages spoken in Europe, and the mobility of its population, there is a high demand for these services to be available in many languages. In order to satisfy this demand, we need to rely on automatic translation, as it is infeasible to manually translate into all languages requested.

The aim of HimL is to use recent advances in machine translation to create and deploy a system for the automatic translation of public health information, with a special focus on meaning preservation. In particular, we will include recent work on domain adaptation, translation into morphologically rich languages, terminology management, and semantically enhanced machine translation to build reliable machine translation for the health domain.

The goal will be to create usable, reliable, fully automatic translation of public health information, initially testing with translation from English into Czech, Polish, Romanian and German. In the HimL project we will iterate cycles of incorporating improvements into the MT systems, with careful evaluation and user acceptance testing.

Upcoming events:

11th - 13th May 2015 - The HimL project will be presented at European Association for Machine Translation (EAMT) as a poster presentation.

More information about the project can be found at http://www.himl.eu