MSc Praktikum in Natural Language Processing (08 140750, I=PRAK-1P)
6 SWS, (bi)weekly meetings, block session at the end of the semester
Topic: Geographically Specialized Language Models
Description: The students will work on implementing geographically specialized large pretrained language models that can capture specific properties of dialects and closely related languages (e.g., variants of English -- UK, USA, India, Australia, ...; Norwegian, Swedish, Danish; Croatian, Serbian, Bosnian, Montenegrin). The project will include implementation of a web application (i.e., interface) for making predictions on geolocations (in supervised and zero-shot fashion) given dialectal language as input.
Deliverables: The project is expected to result with a platform for exploring geographically specialized language models, which is to be described in a system demonstration paper to be submitted for a top-tier NLP conference.
6 SWS, (bi)weekly meetings, block session at the end of the semester
Topic: Geographically Specialized Language Models
Description: The students will work on implementing geographically specialized large pretrained language models that can capture specific properties of dialects and closely related languages (e.g., variants of English -- UK, USA, India, Australia, ...; Norwegian, Swedish, Danish; Croatian, Serbian, Bosnian, Montenegrin). The project will include implementation of a web application (i.e., interface) for making predictions on geolocations (in supervised and zero-shot fashion) given dialectal language as input.
Deliverables: The project is expected to result with a platform for exploring geographically specialized language models, which is to be described in a system demonstration paper to be submitted for a top-tier NLP conference.
- Dozent: Goran Glavaš