Projects

The ParlaCAP project leverages advanced natural language processing to analyse political agendas and sentiments in debates from 27 European national parliaments.

By integrating the ParlaMint dataset and the Comparative Agendas Project’s coding scheme, the project will create a comprehensive, FAIR dataset for comparative political research, enhancing transparency and accountability in legislative discourse across Europe.

The project engages leading Slovenian researchers and institutions in the field of language technologies and connects them with the leading researchers and institutions in selected areas of digital humanities. In this way, it fosters innovation and excellence and strengthens the international profile of Slovenian research.

The project aims to complement scientific impact with wider societal impact, using state-of-the-art artificial intelligence and language technologies to transform the digital humanities and to better understand language, history, people and society.

The ARENAS project (Analysis of and Responses to Extremist Narratives) analyses extremist narratives that influence political and social life in Europe. It examines the nature of these narratives and seeks to understand the discourses they influence, in particular on science, gender and nation. By understanding how these narratives work, ARENAS will empower people to resist them. In order to foster a spirit of coexistence among people across Europe, policy recommendations will be made on how to prevent such narratives from taking hold in the future.

ParlaMint is a European CLARIN infrastructure project focusing on creating comparable and uniformly annotated corpora of parliamentary debates in Europe. The first phase of the project (ParlaMint I: 2020-2021) has produced 17 corpora, while the second phase (ParlaMint II: 2022-2023) is increasing the time span of the corpora, adding corpora for new countries and autonomous regions, providing machine-translated versions of the corpora in English, and further enriching the corpora with additional metadata to improve their usability.

Dr Jakob Lenardič’s postdoctoral project examines the semantic and syntactic properties of certain transformations in the verbal mode in Slovene. The aim of the project is to show that a purely syntactic treatment of binding offers a more accurate model of verb structures than previous lexical approaches in Slovenian linguistics. The project accurately incorporates the properties of language that are evidenced in actual use and contributes to a better understanding of the cognitive processes underlying the semantic-concordant construction of Slovene grammatical structures.