Published multiple scientific articles, such as 'NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark' and 'An Expanded Massive Multilingual Dataset for High-Performance Language Technologies (HPLT)'.
Research Experience
Involved in several projects, including a suite of Norwegian LMs (NorBERT-3 and NorT5), an efficient LM architecture (LTG-BERT), tokenization with Factorized Subword Encoding, and ChatNorT5 – a conversational agent based on NorT5.
Education
Pursuing a PhD at the Language Technology Group at the University of Oslo, as part of the dScience center.
Background
PhD student with a primary academic interest in language modeling, particularly how to make large pre-trained language models more efficient and effective. Also interested in parsing semantic graphs from time to time.