Fysikkbygningen øst (kart)
Sem Sælands vei 24
We have just released a new dataset for modeling sentence-level polarity for Norwegian: NoReCsentence
Today, Titan.uio.no writes about sentiment analysis and how the SANT work will be continued in two new Centres for Research-based Innovation.
SANT and opinion mining to be presented at the upcoming Impact Breakfast about AI.
Two new papers from SANT were presented at the NoDaLiDa conference.
The SANT project will be presented at the Cutting Edge Festival.
Word--context vector space models can be used for measuring the semantic similarity between words based on their contextual distributions across large text collections. In this project we propose to use such models for automatically extending a semantic lexicon, such as a wordnet. The scope could also be restricted to a certain set of classes, say focusing only on emotion words as encoded in for example WordNet-Affect.