Leiden University Centre for Digital Humanities
Corpus linguistics, machine learning, computer vision
Exploring new methods in comparing sign language corpora. The goal of this project is to innovate some of the most widely used tools in the analysis of signed languages. This will include the expansion of the functionalities of SignBank which is a lexical database for sign language corpora, with the purpose of enabling cross-corpus compatibility. Further, the project will also explore ways in which automated image analysis can be used for semi-automated lemma generation. The functionalities will be developed based on the collection of corpora of four African sign languages that were compiled at the Leiden University.
Currently the focus of the project is the development of a tool that utilizes dimensionality reduction techniques in order to analyze and interpret the lexical and phonological variation between different sign languages. Additionally, the application of deep learning techniques for the extraction of phonological features from sign language videos is being explored. The project is in collaboration with the Leiden University Centre for Linguistics and the Leiden Univesrity Centre for Digital Humanities.
Manolis gained his Bachelor from the department of Digital Systems at the University of Piraeus in Greece. After working as a mathematics and informatics tutor, he came to the Netherlands to attend the Media Technology master's program at Leiden University’s Computer Science Institute. He had been working as a software and web developer, and he is currently a Ph.D. student under the supervision of Victoria Nyst.