Hi there ๐
- ๐ญ My research is on natural language processing and machine learning. I'm currently looking at:
- ๐ LLM security: language model harms manifest if we don't treat them as unreliable and subvertible. Follow @llm_sec
- ๐ก๏ธ Online harms: misinformation processing, hate speech & abusive language detection. Work safely with this data!
- ๐ฑ Efficient machine learning: we should be able to do more with much less than we have; always interested in data efficiency and greener, smaller, faster ๐, coarser models. Read our survey on efficient NLP in TACL!
- โ๏ธ Generation: Creating meaningful sequences from a set of items is hard! See our ICML paper on set2seq methods and the catalog problem
- ๐ฉ๐ฐ NLP for Danish: I started and run the Danish Gigaword project
-
๐ข I'm principal investigator of the Strรธmberg NLP group at ITU Copenhagen & visiting professor at UW NLP for my day job
-
๐งโ๐ Iโm still learning sizecoding
-
๐ My reearch papers are on Google Scholar. Ask me about any of them!
-
๐ชถ I write NLP, machine learning, and language tech articles on my blog, Inter Human Agreement