PhD Candidate for Transfer Learning for Federated Search

PhD Candidate for Transfer Learning for Federated Search

Published Deadline Location
2 Oct 27 Oct Nijmegen

You cannot apply for this job anymore (deadline was 27 Oct 2019).

Browse the current job offers or choose an item in the top navigation above.

Job description

We are looking for a PhD candidate to join the Data Science group at Radboud University for an exciting new project on transfer learning for language modelling with an application for federated search. Transfer learning learns general purpose language models from huge datasets, such as web crawls, and then trains the models further on smaller datasets for a specific task. Transfer learning in NLP has successfully used pre-trained word-embeddings for several tasks. Although the success of word embeddings on search tasks has been limited, recently pre-trained general purpose language representations such as BERT and ELMo have been successful on several search tasks, including question answering tasks and conversational search tasks. Resource descriptions in federated search consist of samples of the full data that are sparser than full resource representations. This raises the question of how to infer vocabulary that is missing from the sampled data. A promising approach comes from transfer learning from pre-trained language representations. An open question is how to effectively and efficiently apply those pre-trained representations and how to adapt them to the domain of federated search. In this project, you will use pre-trained language models, and further train those models for a (federated) search task. You will evaluate the quality of those models as part of international evaluation conferences like the Text Retrieval Conference (TREC) and the Conference and Labs of the Evaluation Forum (CLEF). Real world applications of federated search are pursued in cooperation with Sound and Vision in the Netherlands by contributing to a federated search engine for images from a large number of Dutch municipalities and museums.

Specifications

Radboud University

Requirements

  • An MSc degree in computer science or a related field.
  • Excellent programming skills.
  • Good social skills and a good command of spoken and written English.

Conditions of employment

Fixed-term contract: your performance will be evaluated after 18 months. If the evaluation is positive, the contract will be extended.

  • Employment: 32 - 40 hours per week.
  • A maximum gross monthly salary of € 2.972 based on a 38-hour working week (salary scale P).
  • The exact salary depends on the candidate's qualifications and amount of relevant professional experience. The starting salary is €2,325 per month on a full-time basis, the salary will increase to €2,972 per month in the fourth year (P scale)
  • In addition to the salary: an 8% holiday allowance and an 8.3% end-of-year bonus.
  • Duration of the contract: your performance will be evaluated after 18 months. If the evaluation is positive, the contract will be extended
  • You will be able to make use of our Dual Career Service: our Dual Career Officer will assist with family-related support, such as child care, and help your partner prepare for the local labour market and with finding an occupation.
  • Are you interested in our excellent employment conditions?

Employer

Radboud University

We want to get the best out of science, others and ourselves. Why? Because this is what the world around us desperately needs. Leading research and education make an indispensable contribution to a healthy, free world with equal opportunities for all. This is what unites the more than 22,000 students and 5,000 employees at Radboud University. And this requires even more talent and collaboration. You have a part to play!

Department

Faculteit der Natuurwetenschappen, Wiskunde & Informatica

You will be appointed at the Data Science section of the Institute for Computing and Information Sciences (ICIS). During recent evaluations, ICIS has been consistently ranked as the No. 1 Computing Science department in the Netherlands. Evaluation committees praised our flat and open organisational structure, our ability to attract external funding, our strong ties to other disciplines, and our solid contacts with government and industrial partners. The Data Science group is well known for its contributions to mathematical models of information retrieval and the empirical evaluation of such models on large datasets. Strategically located in Europe, Radboud University is one of the leading academic communities in the Netherlands. Radboud University is an equal opportunity employer, committed to building a culturally diverse intellectual community, and as such encourages applications from women and minorities. The university offers customised facilities to better align work and private life. Parents are entitled to partly paid parental leave and Radboud University employees enjoy flexibility in the way they structure their work. The university highly values the career development of its staff, which is facilitated by a variety of programmes.

Specifications

  • PhD
  • Natural sciences
  • 32—40 hours per week
  • max. €2972 per month
  • University graduate
  • 1064653

Employer

Location

Houtlaan 4, 6525 XZ, Nijmegen

View on Google Maps

Interesting for you