Building a Swedish Open-Domain Conversational Language Model
This addresses the problem of limited conversational AI resources for Swedish speakers, though it is incremental as it adapts existing methods to a new language and dataset.
The researchers tackled the challenge of creating a Swedish open-domain conversational language model by training on data from the Flashback forum, and a pilot human evaluation showed the model often responds in a human-like and informative way across diverse topics.
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.