Yova Kementchedjhieva
Assistant Professor of Natural Language Processing
Research interests
Kementchedjhieva’s research concerns language generation in multimodal and cross-lingual contexts. She is interested in knowledge grounding and transfer learning, most recently in the area of vision-and-language processing. Email
Prior to joining MBZUAI, Kementchedjhieva was a postdoctoral researcher in the department of computer science at the University of Copenhagen. During her time at the University of Copenhagen, she worked on conditional text generation across a range of tasks, including grammatical error correction, dialog generation and image captioning. Her earlier work concerned multilingual natural language processing, with a focus on cross-lingual embedding alignment.
While at Copenhagen, she also worked as a teaching assistant, gave lectures for beginner and advanced NLP courses, and interned at Google LLC. and DataMinr in a researcher capacity.
- Ph.D. in computer science from the University of Copenhagen
- Master of Science in cognitive science from the University of Edinburgh
- Master of Arts (equivalent to B.Sc.) in linguistics from the University of Edinburgh.
- Rita Ramos, Bruno Martins, Desmond Elliott, Yova Kementchedjhieva. SmallCap: lightweight image captioning prompted with retrieval augmentation. In Proceedings of CVPR 2023.
- Yova Kementchedjhieva & Ilias Chalkidis. An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text. In Findings of ACL 2023.
- Yova Kementchedjhieva, Anders Søgaard. Grammatical Error Correction through Round-Trip Machine Translation. In Findings of EACL 2023.
- Mareike Hartmann, Miryam de Lhoneux, Daniel Hershcovich, Yova Kementchedjhieva, Lukas Nielsen, Chen Qiu, Anders Søgaard. A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs. In Proceedings of CoNLL 2021.