Research assistant in Computational Linguistics - Hiring in process/Finished, not possible to apply

The Department of Linguistics and Philology is involved in research and education in a number of
languages and language-related subjects and provides an international work environment. The
department’s activities cover many of the classical and modern languages and cultures in large areas of Europe,Asia and Africa, as well as computational and general linguistics. Education is offered at the Bachelor, Master and PhD levels.

Project description
This position is part of the research project Labour's Memory. Digitization of annual and financial reports of blue-collar worker unions 1880-2020, financed by Riksbankens Jubileumsfond. The aim of this project is to collect and digitize annual and financial reports from local, regional, national and international trade union organisations from 1880 onwards. Languages involved are mainly Swedish, English and German, and to some extent also French and Dutch. The collection is stored in a database, and the contents are made searchable through a user portal. The project is carried out in a collaboration between labour history experts, archivists, computational linguists and image analysis specialists.

In the computational linguistics part of the project, we focus on Named Entity Recognition techniques for enhanced searchability options and for automatic metadata generation. Since the documents in the collection span from 1880 to present-day texts, we also need to handle old and non-standard spelling, mainly by including spelling normalisation techniques. Furthermore, as the project covers several languages, we are also interested in automatic language detection. A fourth area of interest within the project is topic modelling, where we hope to be able to automatically distinguish topics of interest to the labour movement over time, nationally and internationally.

Duties
A subset of the below:

• Training and adaptation of named-entity recognition systems for Swedish, English, German, French and Dutch
• Implementation of automatic language detection for the above languages, or a subset of them
• Application of spelling normalisation techniques for historical versions of the above languages, or a subset of them
• Application of topic modelling to distinguish trends in one or more languages

Requirements

• Bachelor’s degree in language technology, computational linguistics, computer science, linguistics or a language subject
• Documented competence in developing computer programs for processing linguistic data
• Very good oral and written proficiency in English

Additional qualifications

• Proficiency in Swedish, German, French and/or Dutch
• Experience with digital humanities/digital philology

Applications should be in English or Swedish and must include:

• Motivation letter
• CV
• Degree certificate

About the employment
The employment is a temporary position for 7 months. Scope of employment 50 %. Starting date 1 March 2024 or as agreed. Placement: Uppsala.

For further information about the position please contact: Eva Pettersson, eva.pettersson@lingfil.uu.se.

Please submit your application by 14 February 2024, UFV-PA 2024/290.