In recent years, neural network based approaches (i.e. deep learning) have been the main models for state-of-the-art systems in natural language processing, whether that is in machine translation, natural language inference, language modeling or sentiment analysis.
Språkbanken Text är en avdelning inom Språkbanken.
Blogg
- Kristina Lundholm Fors
In our research group, we are exploring ways of analysing language to find early signs of possible cognitive impairment, which may develop to dementia.
At Språkbanken we collect resources, mainly lexica and corpora, most of them in Swedish. So far we have collected Swedish corpora totalling 13 billions of words, in all kinds of genres and from all time periods.
Among the flurry of Språkbanken’s historical resources we find the Kubhist corpus – a diachronic collection of historical newspaper texts – in two versions: Kubhist 1 spanning the time period of 1750–1950, and Kubhist 2 spanning the time period of 1645–1926.
One of the most central aspects of language learning is the learning of words.
Ordet tsunami var helt okänt för de flesta i Sverige före julhelgen 2004. Då inträffade ju det som så småningom kom att kallas tsunamikatastrofen, en förfärlig naturkatastrof som skördade otaliga dödsoffer i Sydasien och Sydostasien.