Jussi Karlgren

Jussi Karlgren is a Swedish computational linguist, research scientist at Spotify, and co-founder of text analytics company Gavagai AB.[1] He holds a PhD in computational linguistics from Stockholm University,[2] and the title of docent (adjoint professor) of language technology at Helsinki University.[3]

Jussi Karlgren is known for having pioneered the application of computational linguistics to stylometry,[4] for having first formulated the notion of a recommender system,[5][6][7] and for his continued work in bringing non-topical features of text to the attention of the information access research field.

Karlgren's research is focused on questions relating to information access, genre and stylistics, distributional pragmatics, and evaluation of information access applications and distributional models.

Karlgren is of half Finnish descent and is fluent in Finnish.[8]

References

  1. ^ "About Us". Gavagai. Retrieved 6 February 2022.
  2. ^ "Institutionen för lingvistik: avhandlingar". Stockholms universitet. Retrieved 6 February 2022.
  3. ^ "Language Technology". Helsinki University. Retrieved 6 February 2022.
  4. ^ Karlgren, Jussi; Cutting, Douglass (1994). "Recognizing Text Genres with Simple Metrics Using Discriminant Analysis". Proceedings of the International Conference on Computational Linguistics. 2: 1071. arXiv:cmp-lg/9410008. Bibcode:1994cmp.lg...10008K. doi:10.3115/991250.991324. S2CID 1297432.
  5. ^ Karlgren, Jussi. 1990. "An Algebra for Recommendations." Syslab Working Paper 179 (1990).
  6. ^ Karlgren, Jussi. "Newsgroup Clustering Based On User Behavior-A Recommendation Algebra." SICS Research Report (1994).
  7. ^ Karlgren, Jussi (October 2017). "A digital bookshelf: original work on recommender systems". Retrieved 27 October 2017.
  8. ^ "Ihan varmasti on vaikutusta". sverigesradio.se (in Finnish). 23 October 2013. Retrieved 7 March 2018. Jussi Karlgren: "meitä oli aika monta, jotka – niin kuin minäkin – että yksi vanhemmista oli suomalainen" (c. 6:19–6:25 in the radio interview)