Markos Stamatakis

Number of publications: 5

2024

1. [1]

   A. Brack, E. Entrup, M. Stamatakis, P. Buschermöhle, A. Hoppe, and R. Ewerth:

   Sequential sentence classification in research papers using cross-domain multi-task learning

   International Journal on Digital Libraries, 2024.

   https://doi.org/10.1007/s00799-023-00392-z

   Bib

   The automatic semantic structuring of scientific text allows for more efficient reading of research articles and is an important indexing step for academic search engines. Sequential sentence classification is an essential structuring task and targets the categorisation of sentences based on their content and context. However, the potential of transfer learning for sentence classification across different scientific domains and text types, such as full papers and abstracts, has not yet been explored in prior work. In this paper, we present a systematic analysis of transfer learning for scientific sequential sentence classification. For this purpose, we derive seven research questions and present several contributions to address them: (1) We suggest a novel uniform deep learning architecture and multi-task learning for cross-domain sequential sentence classification in scientific text. (2) We tailor two transfer learning methods to deal with the given task, namely sequential transfer learning and multi-task learning. (3) We compare the results of the two best models using qualitative examples in a case study. (4) We provide an approach for the semi-automatic identification of semantically related classes across annotation schemes and analyse the results for four annotation schemes. The clusters and underlying semantic vectors are validated using k-means clustering. (5) Our comprehensive experimental results indicate that when using the proposed multi-task learning architecture, models trained on datasets from different scientific domains benefit from one another. Our approach significantly outperforms state of the art on full paper datasets while being on par for datasets consisting of abstracts.

           @article{Brack2024,
     author = {Brack, Arthur and Entrup, Elias and Stamatakis, Markos and Buschermöhle, Pascal and Hoppe, Anett and Ewerth, Ralph},
     journal = {International Journal on Digital Libraries},
     title = {Sequential sentence classification in research papers using cross-domain multi-task learning},
     year = {2024},
     issn = {1432-1300},
     doi = {10.1007/s00799-023-00392-z},
     refid = {Brack2024},
     url_ = {https://doi.org/10.1007/s00799-023-00392-z}
   }

2. [2]

   J. Berger, J. Koß, M. Stamatakis, A. Hoppe, R. Ewerth, and C. Wartena:

   Question Generation Capabilities of “Small" Large Language Models

   In: International Conference on Natural Language & Information Systems, NLDB 2024, Turin, Italy, June 25-27, 2024. Springer, 2024.

   Accepted for Publication

   Bib

           @inproceedings{berger2024llms,
     author = {Berger, Joshua and Koß, Jonathan and Stamatakis, Markos and Hoppe, Anett and Ewerth, Ralph and Wartena, Christian},
     title = {Question Generation Capabilities of ``Small" Large Language Models},
     booktitle = {International Conference on Natural Language & Information Systems,
                       {NLDB} 2024, Turin, Italy, June 25-27, 2024},
     publisher = {Springer},
     year = {2024},
     status = {unpublished}
   }

2023

1. [1]

   M. Springstein, M. Stamatakis, M. Plank, J. Sittel, R. Mauer, O. Bulgakowa, R. Ewerth, and E. Müller-Budack:

   TIB AV-Analytics: A Web-based Platform for Scholarly Video Analysis and Film Studies

   In: ACM Conference on Research and Development in Information Retrieval, SIGIR 2023, Taipei, Taiwan, July 23-27, 2023, pp. 3195–3199. ACM, 2023.

   https://doi.org/10.1145/3539618.3591820

   Bib

           @inproceedings{DBLP:conf/sigir/SpringsteinSPSM23,
     author = {Springstein, Matthias and Stamatakis, Markos and Plank, Margret and Sittel, Julian and Mauer, Roman and Bulgakowa, Oksana and Ewerth, Ralph and M{\"{u}}ller{-}Budack, Eric},
     editor_ = {Hsin{-}Hsi Chen and
                       Wei{-}Jou (Edward) Duh and
                       Hen{-}Hsen Huang and
                       Makoto P. Kato and
                       Josiane Mothe and
                       Barbara Poblete},
     title = {{TIB} AV-Analytics: {A} Web-based Platform for Scholarly Video Analysis
                       and Film Studies},
     booktitle = {{ACM} Conference on Research and Development in Information Retrieval, {SIGIR} 2023, Taipei, Taiwan, July 23-27, 2023},
     pages = {3195--3199},
     publisher = {{ACM}},
     year = {2023},
     url_ = {https://doi.org/10.1145/3539618.3591820},
     doi = {10.1145/3539618.3591820},
     timestamp = {Fri, 21 Jul 2023 22:25:24 +0200},
     biburl = {https://dblp.org/rec/conf/sigir/SpringsteinSPSM23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

2. [2]

   M. Stamatakis, W. Gritz, J. Oldag, A. Hoppe, S. Schanze, and R. Ewerth:

   Automatic Analysis of Student Drawings in Chemistry Classes

   In: International Conference on Artificial Intelligence in Education, AIED 2023, Tokyo, Japan, July 3-7, 2023, pp. 824–829. Springer, 2023.

   https://doi.org/10.1007/978-3-031-36272-9_78

   Bib

           @inproceedings{stamatakis2023automatic,
     author = {Stamatakis, Markos and Gritz, Wolfgang and Oldag, Jos and Hoppe, Anett and Schanze, Sascha and Ewerth, Ralph},
     editor_ = {Ning Wang and
                       Genaro Rebolledo{-}Mendez and
                       Noboru Matsuda and
                       Olga C. Santos and
                       Vania Dimitrova},
     title = {Automatic Analysis of Student Drawings in Chemistry Classes},
     booktitle = {International Conference on Artificial Intelligence in Education,
                       {AIED} 2023, Tokyo, Japan, July 3-7, 2023},
     series_ = {Lecture Notes in Computer Science},
     volume_ = {13916},
     pages = {824--829},
     publisher = {Springer},
     year = {2023},
     url_ = {https://doi.org/10.1007/978-3-031-36272-9\_78},
     doi = {10.1007/978-3-031-36272-9\_78},
     timestamp = {Fri, 07 Jul 2023 23:30:38 +0200},
     biburl = {https://dblp.org/rec/conf/aied/StamatakisGOHSE23.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org}
   }

2022

1. [1]

   C. Otto, M. Stamatakis, A. Hoppe, and R. Ewerth:

   Predicting Knowledge Gain for MOOC Video Consumption

   In: International Conference on Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium, AIED 2022, Durham, UK, July 27-31, 2022, pp. 458–462. Springer, 2022.

   https://doi.org/10.1007/978-3-031-11647-6_92

   Bib

           @inproceedings{otto2022predicting,
     author = {Otto, Christian and Stamatakis, Markos and Hoppe, Anett and Ewerth, Ralph},
     editor_ = {Maria Mercedes T. Rodrigo and Noburu Matsuda and Alexandra I. Cristea and Vania Dimitrova},
     title = {Predicting Knowledge Gain for {MOOC} Video Consumption},
     booktitle = {International Conference on Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners' and Doctoral Consortium, {AIED} 2022, Durham, UK, July 27-31, 2022},
     series_ = {Lecture Notes in Computer Science},
     volume_ = {13356},
     pages = {458--462},
     publisher = {Springer},
     year = {2022},
     doi = {10.1007/978-3-031-11647-6_92},
     timestamp = {Mon, 08 Aug 2022 21:23:09 +0200},
     biburl = {https://dblp.org/rec/conf/aied/OttoSHE22.bib},
     bibsource = {dblp computer science bibliography, https://dblp.org},
     keywords = {ownwork}
   }