Computer Linguistics in Nederlands

Vacancies for two computer linguists

The Institute for Dutch Lexicology has two vacancies for experienced computer linguists for the development of Named Entity Processing tools for IMPACT.

IMPACT is a new European research project in the field of informatics for the humanities. The project will start on 1 january 2008. In IMPACT 15 National libraries and research institutes from Europe, Israel and Russia will work together.

The main purpose of IMPACT is to obtain a significant improvement of the accessibility of historical documents.

To achieve this, the following will be tackled:

Current OCR-software is not suitable for mass digitisation of historical documents. Within the project, OCR software will be developed that will significantly improve the accuracy of state -of-the-art systems, so as to enable for the first time, reliable full text mass digitisation of historical documents.
Information in historical documents is not easily accessed by modern users because of the historical language barrier. Within the project, historical lexica and linguistic processing tools will be developed that will enable enriched indexing to provide access historical material with contemporary query.
To be effective the lexica will also have to contain Named Entity data and tools for NE recognition and NE classification for historical language material will have to be developed.

Tasks

The NE specialists will be responsible for the development of a toolbox for NE lexicon building and NE lexicon deployment to tackle historical language material to be used for the improvement of OCR of historical texts and for better retrieval on historical text material. The work will imply the implementation as well as the design of relevant algorithms.

Profile

• relevant background in computational linguistics, computer science or applied mathematics (master level, preferably PHD level)
• sufficient knowledge and experience with the development and implementation of NLP algorithms, preferably in the field of NE processing
• sufficient experience in developing complex software systems; preferably proficiency in C, C++ and/or Java
• knowledge of Dutch language is required, preferably knowledge of historical Dutch language

Offer

An INL contract for two years. According to the cao–Onderzoekinstellingen the salary scale indicated for this job is 11 max., with a maximum of € 4.138, - gross per month on the basis of a 40 hour week. In addition you will be entitled to 42 days holiday per year plus holiday pay.

Interested

Contact Katrien Depuydt (Taalbank) INL, Postbus 9515, 2300 RA, Leiden

tel. (+31 (0)71 527 2479), email: depuydt@inl.nl.

Send your application to Dr. Jeannine Beeken, INL, Postbus 9515, 2300RA Leiden, email: secretariaat@inl.nl

Closing date: 02-01-2008