Tuesday seminar with Martin Søyland
PhD Candidate Martin Søyland will present the Talk of Norway project with description, how to get involved, and examples of usage.
Talk of Norway is an ongoing cross-disciplinary collaboration, where researchers in Language Technology (LT) and Political Science (PS) are applying machine learning methods to data from the Norwegian parliament in order to gather knowledge spanning across different dimensions.
The Talk of Norway (ToN) dataset is an open source collection of 250373 Speeches from the Norwegian Parliament from 1998 to 2016. The speeches come with a rich set of 83 metadata variables, and are annotated with sentence and token boundaries, lemmas, parts-of-speech and morphological features.
In terms of research, the project aims at testing central theories in political science, using speech and state of the art tools from Natural Language Processing.
More information can be found at: http://www.mn.uio.no/ifi/english/research/projects/ton/