Natural Language Processing For Expert Domains (ExpNLP)

At ExpNLP, we work on Natural Language Processing applied to expert domains, with a focus on the real-world impact of AI.

Our interests include:

  • Evaluation of Large Language Models in expert domains including software engineering, healthcare, and industry dynamics.
  • Reliable integration of multimodal data in AI to help domain experts in their work.
  • Expert-AI interaction and collaboration.

People

PhD Students

Doan

Doan Nam Long Vu

Topics: Multimodal AI for mental health

TODO - bio


Anna

Anna Mokhova

Topics: Expert-AI collaboration in coding

TODO - bio


Ruilong

Ruilong Wang

Topics: Multimodal RAG systems for automotive applications

TODO - bio


Student Thesis

Finished

  • Enhancing Natural Language Inference in Biomedical Applications Using Large Language Models (finished) — Kai Zhao, supervised by Dr. Simone Balloccu

Ongoing

  • Time-Stamped Graphs for Cross-Year Reasoning in VolksWagen Annual Reports (ongoing) — Karim Abdelrahman, supervised by Ruilong Wang
  • Contrast Set Generation for Evaluation QA Models in Annual Report reasoning (ongoing) — Cagin Senemoglu, supervised by Ruilong Wang
  • Expressive Text-To-Speech Generation and Evaluation for Therapist-Client Dialogues (ongoing) — Marleen Sinsel, supervised by Doan Nam Long Vu
  • Synthetic Therapist-Client Conversation Generation From Questionnaires (ongoing) — Mohamed Aziz Boudabous, supervised by Doan Nam Long Vu

Openings / Collaboration

If you are interested in working with us, feel free to get in touch!

At the moment, we welcome application from B.Sc. and M.Sc. thesis students who want to work on compatible topics. If you are interested, feel free to contact Dr. Simone Balloccu. If possible include a grade transcript, an initial topic (or at least proposals), and a CV.

Application for internships are currently considered only if the candidate is self-funded (or virtual). Candidates are welcome to contact Dr. Simone Balloccu with topic proposals. We strongly suggest to highlight the overlapping between your proposal and the existing research directions of the ExpNLP.