In natural language processing, text needs to be transformed into a machine-readable representation before any processing. The quality of further natural language processing tasks greatly depends on the quality of those representations. In this survey, we systematize and analyze 50 neural models from the last decade. The models described are grouped by the architecture of […]
Laboratory for Natural Speech and Language processing
Multilayer Framework for the Information Spreading Characterization in Social Media during the COVID-19 Crisis (InfoCoV)
Communication through social media has been gaining importance in responses to major crises, such as COVID-19. In emergency situations, there is an urgent need to rely on trustworthy information. On the other side, we are all witnessing a huge amount of misinformation (fake news, conspiracy theories) also spreading on social media, especially during a crisis. […]
Corpus-Based Paraphrase Detection Experiments and Review
Paraphrase detection is important for a number of applications, including plagiarism detection, authorship attribution, question answering, text summarization, text mining in general, etc. In this paper, we give a performance overview of various types of corpus-based models, especially deep learning (DL) models, with the task of paraphrase detection. We report the results of eight models […]
H2020 MESOC
MESOC is a Research and Innovation Action designed to propose, test and validate an innovative and original approach to measuring the societal value and impacts of culture and cultural policies and practices, related to three crossover themes of the new European Agenda for Culture: 1) Health and Wellbeing, 2) Urban and Territorial Renovation and 3) […]
Structural Analysis of Factual, Conceptual, Procedural, and Metacognitive Knowledge in a Multidimensional Knowledge Network
Discovering the most suitable network structure of the learning domain represents one of the main challenges of knowledge delivery and acquisition. We propose a multidimensional knowledge network (MKN) consisting of three components: multilayer network and its two projections. Each network layer constitutes factual, conceptual, procedural, or metacognitive knowledge within the domain of databases as a […]
Netokracija on WiDS 2020
Netokracija on the participation of AIRI members Sanda Martinčić-Ipšić and Marina Ivašić Kos in Women in Data Science 2020 conference in Zagreb.
WiDS Conference 2020
Sanda Martinčić-Ipšić participated in the round table on past, present and future of data science at Women in Data Science Conference 2020 in Zagreb from 04-05.03.2020.
AIRI Researchers @ HTV
Ana Meštrović participated in the HTV show “Kod nas doma”. The topic was dedicated to the collaboration between AIRI researchers and OmoLab in the development of the mobile application for dyslexia.
AIRI scientists interview @ Novi List
AIRI scientists reveal in interview for Novi list how their paper on Croatian syllabification helped in creating OmoReader application that allows people with dyslexia to read (pdf), 26.12.2019. A. Meštrović, M Matešić and S. Martinčić-Ipšić received “1st Technology Transfer” award, by University of Rijeka Foundation and company Alarm automatika, for the SyllAssist work on the algorithm for Croatian […]
Multi3Generation: Multi-task, Multilingual, Multi-modal Language Generation
Language generation (LG) is a crucial technology if machines are to communicate with humans seamlessly using human natural language. A great number of different tasks within Natural Language Processing (NLP) are language generation tasks, and being able to effectively perform these tasks implies (1) that machines are equipped with world knowledge that can require multi-modal […]
