[Corpora-List] Multilingual Machine Translation and Text Mining Position at the Joint Research Centre - European Commission

[marco turchi]

On behalf of the Optima Team at the Joint Research Centre - European
Commission

==================================================================

Please pass onto any potentially interested parties.
Apologies for cross-posting.

==================================================================

The Optima Team at the Joint Research Centre - JRC - European Commission is
currently looking for a Postdoctoral Researcher in the fields of
Multilingual Machine Translation and Text Mining.

The successful candidate will help improve and extend several text mining
applications, but to a large extent s/he will work on improving and
extending the JRC’s in-house machine translation (MT) system ONTS (OPTIMA
News Translation System). ONTS is a predominantly statistical MT system
based on Moses, but it additionally makes use of JRC’s in-house resources
(e.g. lists of person names and their variants across different languages
and scripts). To date, ONTS has been trained for 11 language pairs (all
into English). See http://optima.jrc.it/Translate/ for a demo of the
current status of ONTS and the publication “ONTS: OPTIMA News Translation
System” (Turchi et al., EACL’2012) for a technical description of the work
carried out so far.

Possible research avenues related to improving the machine translation
results include (a) finding and gathering more training data; (b)
exploiting comparable news collections to improve the MT performance; and
(c) investigating pre-processing techniques for morphologically complex
languages. Further possible research avenues are related to using MT
technology (d) to improve other text mining tools, e.g. event extraction,
cross-lingual linking of related news or multilingual document
categorisation. Much will be left to the initiative of the candidate as
long as the efforts are targeted towards the objective of the OPTIMA action.

The system within which the results will be deployed is implemented in Java
as a set of servlets in Tomcat and the data processing chain makes
extensive use mark-up languages. Java programming skills and experience
with mark-up languages are therefore required.

Qualifications:

   - University degree in computational linguistics, computer science or
   related areas;
   - Doctoral degree in a similar discipline, or equivalent work experience
   of 5 years;
   - Good written and spoken English language skills are required.  Given
   the strong focus on multilinguality in the work, at least passive knowledge
   of other languages is also required.
   - Programming skills in Java;
   - Hands-on experience with Moses or other, similar statistical machine
   translation engines;
   - Experience in an application-oriented setting would be beneficial;
   - Ability to write scientific publications;
   - Team player, proactive in research, as well as an ability to work
   independently and to communicate efficiently.

Indicative duration: 36 months
Preferred starting date: ASAP

JRC site: Ispra, Italy

**CLOSING DATE FOR APPLICATIONS: 16/09/2012 23:59 CET**

Further Information: http://recruitment.jrc.ec.europa.eu/?type=GH
Code: 2012-IPR-G-30-000-00481 - CAT 30 - ISPRA
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20120730/fc758dcb/attachment.htm>
-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora