Despina-Athanasia Pantazi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Despina-Athanasia Pantazi has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Manolis Koubarakis
National and Kapodistrian University of Athens, Athens, Greece
4 shared publications - Maria Tsourma
National and Kapodistrian University of Athens
2 shared publications - Orestis-Minas Kapopoulos
King’s College London
2 shared publications - Vasileios Kyriakopoulos
National and Kapodistrian University of Athens
2 shared publications - Andreas Both
DATEV eG Germany
1 shared publication - Christoph Lange
Fraunhofer FIT Sankt Augustin Germany
1 shared publication
Latest Publications
- 18 October 2026
- Published by Springer Nature
- p. 3-17
Cardinal Direction Reasoning Using Large Reasoning Models
- 18 October 2026
- Published by Springer Nature
- p. 3-17
Cardinal Direction Reasoning Using Large Reasoning Models
- Open Access
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 81-91
Can Large Reasoning Models Reason about Spatial Relations?
- 3 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 81-91
Open AccessCan Large Reasoning Models Reason about Spatial Relations?
- Open Access
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
The Large Language Model GreekLegalRoBERTa
- 11 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessThe Large Language Model GreekLegalRoBERTa
- Open Access
Template-Based Question Answering over Linked Geospatial Data
Large amounts of geospatial data have been made available recently on the linked open data cloud and the portals of many national cartographic agencies (e.g., OpenStreetMap data, administrative geographies of various countries, or land cover/land use data sets). These datasets use various geospatial vocabularies and can be queried using SPARQL or its OGC-standardized extension GeoSPARQL. In this paper, we go beyond these approaches to offer a question-answering engine for natural language questions on top of linked geospatial data sources. Our system has been implemented as re-usable components of the Frankenstein question answering architecture. We give a detailed description of the system's architecture, its underlying algorithms, and its evaluation using a set of 201 natural language questions. The set of questions is offered to the research community as a gold standard dataset for the comparative evaluation of future geospatial question answering engines.
Open AccessTemplate-Based Question Answering over Linked Geospatial Data
Large amounts of geospatial data have been made available recently on the linked open data cloud and the portals of many national cartographic agencies (e.g., OpenStreetMap data, administrative geographies of various countries, or land cover/land use data sets). These datasets use various geospatial vocabularies and can be queried using SPARQL or its OGC-standardized extension GeoSPARQL. In this paper, we go beyond these approaches to offer a question-answering engine for natural language questions on top of linked geospatial data sources. Our system has been implemented as re-usable components of the Frankenstein question answering architecture. We give a detailed description of the system's architecture, its underlying algorithms, and its evaluation using a set of 201 natural language questions. The set of questions is offered to the research community as a gold standard dataset for the comparative evaluation of future geospatial question answering engines.
- 1 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 348-351
Providing Satellite Data to Mobile Developers Using Semantic Technologies and Linked Data
Copernicus is the European program for monitoring the Earth. It consists of a set of complex systems that collect data from satellites and in-situ sensors, process it, and provide users with reliable and up-to-date information on a range of environmental and security issues. Information extracted from Copernicus data is made available to users through Copernicus services addressing six thematic areas: land, marine, atmosphere, climate, emergency and security. The data processed and disseminated puts Copernicus at the forefront of the big data paradigm and gives rise to all relevant challenges: volume, velocity, variety, veracity and value. In this paper we discuss the challenges of big Copernicus data and how the Copernicus program handled them. We also present lessons learned from our project Copernicus App Lab, which takes Copernicus services information and makes it available on the Web using semantic technologies to aid its take up by mobile developers.
- 1 January 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 348-351
Providing Satellite Data to Mobile Developers Using Semantic Technologies and Linked Data
Copernicus is the European program for monitoring the Earth. It consists of a set of complex systems that collect data from satellites and in-situ sensors, process it, and provide users with reliable and up-to-date information on a range of environmental and security issues. Information extracted from Copernicus data is made available to users through Copernicus services addressing six thematic areas: land, marine, atmosphere, climate, emergency and security. The data processed and disseminated puts Copernicus at the forefront of the big data paradigm and gives rise to all relevant challenges: volume, velocity, variety, veracity and value. In this paper we discuss the challenges of big Copernicus data and how the Copernicus program handled them. We also present lessons learned from our project Copernicus App Lab, which takes Copernicus services information and makes it available on the Web using semantic technologies to aid its take up by mobile developers.