Background
I take part in the “Exploring new methods in comparing sign language corpora” project, a collaboration between the Leiden University Centre for Digital Humanities, Centre for Linguistics and the Data Science Research Programme.
The goal of this project is to innovate some of the most widely used tools in the analysis of signed languages. The project will 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 Leiden University.
Research interests
- Sign language recognition
- African sign languages
- Machine learning
- Computer Vision
Publications
Journal articles
- 2021
- Manolis Fragkiadakis, Victoria Nyst and Peter van der Putten. Towards a User-Friendly Tool for Automated Sign Annotation: Identification and Annotation of Time Slots, Number of Hands, and Handshape. Digital Humanities Quarterly 15.1
Conference proceedings
- 2021
- Manolis Fragkiadakis and Peter van der Putten. Sign and Search: Sign Search Functionality for Sign Language Lexica. In Proceedings of the 1st International Workshop on Automatic Translation for Signed and Spoken Languages (AT4SSL), pp. 23–32.
- 2020
- Manolis Fragkiadakis, Victoria Nyst and Peter van der Putten. Signing as Input for a Dictionary Query: Matching Signs Based on Joint Positions of the Dominant Hand. In Proceedings of the 9th LREC2020 Workshop on the Representation and Processing of Sign Language, Marseille, 11-16 May 2020, pp 69-74.
Peer-reviewed conference abstracts
- 2021
- Manolis Fragkiadakis. Quantifying variation in movement and location: comparing the lexicons of American and Ghanaian Sign Language. Presented at the African Sign Languages Workshop at WOCAL 10 doi: 10.17605/OSF.IO/MV2UF
- 2020
- Manolis Fragkiadakis and Victoria Nyst. Find the Sign: Signing as Input for Sign Language Dictionary Search Using Pose Estimation. Presented at the DH Benelux 2020 #GoesOnline, World Wide Web: Zenodo. http://doi.org/10.5281/zenodo.3870467
- 2019
- Manolis Fragkiadakis. To Sign or not to Sign: Automated Generation of Annotation Slots for Sign Language Videos using Machine Learning. Presented at DH 2019
- 2018
- Manolis Fragkiadakis and Victoria Nyst. Measuring Variation in African Sign Languages: a Data Driven Approach. Presented at the DH Benelux 2018
Other scientific contributions
- 2021
- Manolis Fragkiadakis, Victoria Nyst, & Marco Nyarko. (2021). Ghanaian Sign Language Lexicon (Version 1.0) Data set. Zenodo. http://doi.org/10.5281/zenodo.4533753
- 2019
- Manolis Fragkiadakis, Victoria Nyst and Peter van der Putten. Towards a User-Friendly Tool for Automated Sign Annotation. Poster session presented at: TISLR 2019 conference
Contact
m.fragkiadakis at hum.leidenuniv.nl
P.J. Veth
Nonnensteeg 1-3
2311 VJ Leiden
Room number T0.10
News
- https://www.universiteitleiden.nl/en/news/2019/06/detecting-and-comparing-sign-languages
- https://www.universiteitleiden.nl/en/news/2017/05/lucdh-welcomes-new-phd-candidates
Teaching
- Lecturer: Information Visualization and the Humanities (2020)
- Teaching assistant: Hacking the Humanities (2019)
- Teaching assistant: Information Visualization and the Humanities (2018 - 2019)
Academic history
- PhD Data Science, Digital Humanities 2017 - present
- MSc Media Technology, Leiden University 2014 - 2016
- BSc Digital Systems, Major: e-Services, University of Piraeus 2007-2013