Nettsider med emneord «language technology»

Semantic parsing commonly uses graph-structured target representations, transcending simple rooted trees as are common in (surface-)syntactic analysis.  Quantifying graph similarity between system outputs and gold-standard targets is a challenging problem at the interface of graph theory, efficient algorithm design, and computational semantics.

The SANT project will be presented at the Cutting Edge Festival.

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.

Se mer på den engelske nettsiden.

The Talk of Norway (ToN) is now publicly available.

In this ongoing cross-disciplinary collaboration, researchers in Language Technology (LT) and Political Science (PS) are applying supervised and unsupervised machine learning methods to data from the Norwegian parliament in order to gather knowledge spanning across different dimensions.

Graph representations of word embedding models: evaluating existing approaches and possible applications in language data processing and visualization.

The Language Analysis Portal gives non-technical researchers in the Humanities and Social Sciences easy-to-use access to automated language analysis tools that are invoked at the click of a few buttons and execute ‘behind the scenes’ on a national supercomputer.

Design Patterns is a useful software engineering concept that has been applied to object oriented programming.