BM-TOK
Balancing multilingual token vocabularies
How to build the vocabulary of a multilingual language model so that less-resourced languages and non-Latin scripts are represented fairly.
Vani works on multilingual and dialectal NLP, biomedical text mining, and how language models handle cause and effect. Earlier work includes narrative understanding and visual summaries of text.
She holds a PhD in NLP, on machine learning methods for plagiarism detection.
Projects
UBS–IDSIA AI Lab
UBS–IDSIA AI Lab collaboration
The NLP group participates in the collaboration across different NLP-related projects.
ELDI
Dialect identification in short texts
Developed methods to recognise the dialect of short texts such as social media posts, focusing on varieties of Arabic.
INCdid
Dialect identification in noisy text
Developed methods to identify dialects in short, noisy texts, especially between closely related language varieties.
StageAI
Conversational recommendation of performers
With Stagend, improved a platform that matches performers to events, using multilingual question answering to fill in missing information.
Publications with the group
- On the Limitations of Zero-Shot Classification of Causal Relations by LLMs (Work in Progress)
- Edge Labelling in Narrative Knowledge Graphs
- NOVEL2GRAPH: Visual Summaries of Narrative Text Enhanced by Machine Learning