Projekter pr. år
Personlig profil
Forskningsprofil
I am a Postdoctoral Researcher in Natural Language Processing (NLP) with a focus on NLP Applications, with a special focus on NLP for Education. I am advised by Prof. Johannes Bjerva and Prof. Euan Lindsay.
I hold a PhD in NLP from the IT University of Copenhagen (ITU), where I was advised by Prof. Barbara Plank and A/P. Rob van der Goot. I was part of NLPnorth at ITU and MaiNLP at the Ludwig Maximilian University of Munich (LMU). I worked on Computational Job Market Analysis (or NLP for HR), where we investigated how to extract information (e.g., skills) from job ads data and match these to existing resources (e.g., taxonomies).
I am interested in:
- NLP x Education (Postdoc): Can we improve students’ learning by giving them automatic feedback from NLP tools (e.g., language models)? How can we do this over time?
- NLP x HR (PhD): How can we extract relevant skills from job ads and in what way can we match them with existing taxonomies to assist job centers matching candidates to jobs better?
- Resource Creation: My general interests are mostly on resource creation; such as developing annotation guidelines for data annotation, (multilingual) datasets creation in both general and specific domains, and language model training on small and large scale.
Ekspertise relateret til FN’s Verdensmål
I 2015 blev FN's medlemslande enige om 17 Verdensmål til at bekæmpe fattigdom, beskytte planeten og sikre velstand for alle. Denne persons arbejde bidrager til følgende verdensmål:
Emneord
- Datalogi
Fingerprint
- 1 Lignende profiler
Samarbejde i de sidste fem år
Projekter
- 1 Igangværende
-
Digital Twins for Abundant Feedback: Novel Feedback Paradigms via Explainable Multilingual Natural Language Processing
Bjerva, J. (PI (principal investigator)), Lindsay, E. (PI (principal investigator)) & Zhang, M. (Projektdeltager)
01/01/2024 → 31/12/2025
Projekter: Projekt › Forskning
-
All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages
Vayani, A., Dissanayake, D., Watawana, H., Ahsan, N., Sasikumar, N., Thawakar, O., Ademtew, H. B., Hmaiti, Y., Kumar, A., Kuckreja, K., Maslych, M., Ghallabi, W. A., Qin, C., Shaker, A. M., Zhang, M., Ihsani, M. K., Esplana, A., Gokani, M., Mirkin, S. & Singh, H. & 47 flere, , 10 jun. 2025, The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2025. IEEE (Institute of Electrical and Electronics Engineers)Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review
Fil98 Downloads (Pure) -
DaKultur: Evaluating the Cultural Awareness of Language Models for Danish with Native Speakers
Müller-Eberstein, M., Zhang, M., Bassignana, E., Brunsgaard Trolle, P. & van der Goot, R., 29 apr. 2025, 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP). Association for Computational Linguistics, ACL AnthologyPublikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review
Åben adgangFil5 Downloads (Pure) -
HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings
Aavang, R. T., Rizzi, G., Bøggild, R., Iolov, A., Zhang, M. & Bjerva, J., feb. 2025, (Afsendt).Publikation: Working paper/Preprint › Preprint
-
How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scale
Falk, J., Chen, Y., Rafner, J., Zhang, M., Bjerva, J. & Nolte, A., apr. 2025, CHI '25: Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery (ACM), 34 s.Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review
Åben adgang -
Humanity's Last Exam
Center for AI Safety, 24 jan. 2025, (Under udarbejdelse).Publikation: Working paper/Preprint › Preprint
Fil62 Downloads (Pure)
Forskningsdatasæt
-
HiFi-KPI: A Dataset for Hierarchical KPI Extraction from Earnings Filings
Jensen, R. T. A. (Ophavsperson), Rizzi, G. (Ophavsperson), Bøggild, R. (Ophavsperson), Iolov, A. (Ophavsperson), Zhang, M. (Ophavsperson) & Bjerva, J. (Vejleder), Hugging Face, 21 feb. 2025
DOI: 10.57967/hf/4619
Datasæt
-
Retrieval Augmented Skill Extraction
Zhang, M. (Foredragsholder)
28 apr. 2025Aktivitet: Foredrag og mundtlige bidrag › Foredrag og præsentationer i privat eller offentlig virksomhed
Fil -
SnakModel: Lessons Learned from Training an Open Danish Large Language Model
Zhang, M. (Foredragsholder)
19 dec. 2024Aktivitet: Foredrag og mundtlige bidrag › Foredrag og præsentationer i privat eller offentlig virksomhed
-
Evaluating Large Language Models: A Cultural Perspective
Zhang, M. (Foredragsholder)
12 dec. 2024Aktivitet: Foredrag og mundtlige bidrag › Foredrag og præsentationer i privat eller offentlig virksomhed
-
Evaluating Large Language Models: A Cultural Perspective
Zhang, M. (Foredragsholder)
3 dec. 2024Aktivitet: Foredrag og mundtlige bidrag › Foredrag og præsentationer i privat eller offentlig virksomhed
-
Pre-training Large Language Models
Zhang, M. (Foredragsholder)
20 sep. 2024Aktivitet: Foredrag og mundtlige bidrag › Gæsteforelæsning