Nettsider med emneord «sentiment analysis»
Correct scope detection is an important part in making consistent predictions for many NLP tasks, but it can be a difficult problem, both for newer models and for human annotators. This thesis explores how syntactic information can be utilised at different steps of the modelling process.
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.
The SANT project aims to create training data and machine-learned models for Sentiment Analysis for Norwegian Text. While coordinated by the Language Technology Group at IFI/UiO, collaborating partners include NRK, Schibsted and Aller Media.
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.