Master's Thesis projects

If you are a GU or Chalmers student who wants to carry out a Master's Thesis project on a natural language processing topic, please get in touch and we can meet for a discussion. I am quite open to supervising projects in the general NLP area, including topics in syntactic and semantic parsing, topic modeling, various types of entity recognition, etc. I also supervise projects on machine learning topics in general.

In addition, please take a look at the CSE department's guidelines for thesis projects so that you are aware of the relevant regulations and deadlines. Please note that the department strongly prefers thesis projects to be carried out in pairs.

Keep in mind that it's much more likely to find a willing supervisor if you have a research-oriented topic: this applies to me but also to most of the department's supervisors. We are somewhat reluctant in accepting thesis topics defined by companies, as these projects often require a significant amount of work in order to find a relevant research angle.

Here are a few sketches for project proposals that can give you some ideas. Some of these are pure research projects while some are more practically oriented collaborations with companies or public entities. (For the projects that lack a description, please get in touch for more details.)

• Machine learning meets social science: policy causal evaluation with text
• Improving robustness of prompts in language models
• Analysis methods for multimodal language models
• Improved training methods for multimodal language models
• Making NLP applications using large-scale language models more efficient
• Neural network topic models

Feel free to contact me if you have other ideas you'd like to discuss.