M.Sc. Thesis: Classification of grant proposals using natural language processing
We are looking for a dedicated master’s student to join us at the Computer Science department at RISE.
The thesis is a collaboration between the Connected Intelligence and Intelligent Systems Units both part of RISE Computer Science department in Kista. One of the main research topics of the department is artificial intelligence and we are currently heading an applied AI center with NLP as one of the main topics. The thesis will be a collaboration between RISE and Ymner (Oscar Ridell) and will be supported by Joakim Nivre and his team with focus on NLP.
Background and Purpose
Ymner collects and analyses data on calls for proposals and grants from Sweden's public and private funders of research and innovation. In the development of the platform, there is a need for automatic classification of the collected data, which consists of descriptions in running text. The need consists of automatically classifying research projects in accordance with established standards (SCB standard), as well as exploring possibilities for establishing standards for the classification of innovation projects.
The focus of this project is to explore the use of natural language processing techniques to automate the classification of research projects. Given the availability of previously classified proposals that can be used as training data, this is a supervised text classification problem that can be tackled using standard machine learning methods for classification, including fine-tuning of pre-trained language models. Since the SCB classification is hierarchical, it may also be interesting to explore stepwise approaches as a way of improving classification accuracy. A possible extension of the project is to investigate how classification can be extended to innovation projects, which can be viewed as a domain adaptation problem.
- Start Time: As soon as possible
- Scope: 30 hp
- Location: RISE Computer Science, Kista, Stockholm. Option to partially work remotely.
Who are you?
We expect you to have a good knowledge of machine learning with a focus on NLP, good programming skills and an interest in solving complex problems.
Welcome with your application!
To know more, please contact Joakim Eriksson (firstname.lastname@example.org, tel 070 321 3841). Applications should include a brief personal letter, CV, recent grades, and a code excerpt. Candidates are encouraged to send in their application as soon as possible but at the latest by the 15th of December 2022. Suitable applicants will be interviewed as soon as applications are received.
Master thesis, Machine Learning, Natural Language Processing, RISE, Stockholm
Student - examensarbete/praktik
2022-12-15Skicka in din ansökan