Building a Swedish Open-Domain Conversational Language Model
Paper i proceeding, 2021

We present on-going work of evaluating the, to our knowledge, first large generative language model trained to converse in Swedish, using data from the online discussion forum Flashback. We conduct a human evaluation pilot study that indicates the model is often able to respond to conversations in both a human-like and informative manner, on a diverse set of topics. While data from online forums can be useful to build conversational systems, we reflect on the negative consequences that incautious application might have, and the need for taking active measures to safeguard against them.


Tobias Norlund

Data Science och AI 1

Agnes Stenbom

Kungliga Tekniska Högskolan (KTH)

Proceedings of the 23rd Nordic Conference on Computational Linguistics (NoDaLiDa)

978-91-7929-614-8 (ISBN)

23rd Nordic Conference on Computational Linguistics (NoDaLiDa)
Reykjavik, Iceland,


Språkteknologi (språkvetenskaplig databehandling)


Datavetenskap (datalogi)

Mer information

Senast uppdaterat