Processing of text written in natural language

Within the project “The use of ai to automate the rapid integrated assessment mechanism and to nationalize sustainable development goals in Serbia”, an algorithmic solution was developed that measures the degree of agreement between relevant national plans/strategies and (sub)goals from the UN Sustainable Development Agenda, for the Serbian language and smaller and morphologically complex languages related to it.

Problem-solving is based on using a distributional semantic model, which compares the meanings of the description of each sustainable development goal and each sentence/paragraph from the relevant national plans/strategies. The AutoRIA model was trained on the textual content of 129 national plans/strategies and was evaluated on the first five sustainable development goals from the UN Agenda. The obtained results are comparable to the average results of the model for the English language.

The project was financed by the United Nations Development Programme (UNDP).