I am a Ph.D. candidate, part of the IT4BI-DC Erasmus Mundus Doctorate program. Already in the last year of my studies, I have focused my research efforts on semi-structured documents, such as spreadsheets and web-tables. The objective of my thesis is to develop techniques for automatic analysis and processing of such documents. The main goal is to recognize tables, infer their structure, and expose this for further processing.
Gonsior, J.; Rehak, J.; Thiele, M.; Koci, E.; Günther, M.; Lehner, W.
In Workshop Proceedings of the EDBT/ICTDT 2020 Joint Conference.2020.
@article{,
author = {Julius Gonsior and Josephine Rehak and Maik Thiele and Elvis Koci and Michael G\"{u}nther and Wolfgang Lehner},
title = {Active Learning for Spreadsheet Cell Classification},
journal = {Workshop Proceedings of the EDBT/ICTDT 2020 Joint Conference},
year = {2020},
month = {3},
numpages = {6},
url = {https://sea-data.ml/}
}
Romero, O.; Koci, E.; Lehner, W.; Thiele, M.; Gonsior, J.
In The 19th ACM Symposium on Document Engineering (DocEng).2019.
@article{,
author = {Oscar Romero and Elvis Koci and Wolfgang Lehner and Maik Thiele and Julius Gonsior},
title = {XLIndy: Interactive Recognition and Information Extraction in Spreadsheets},
booktitle = {The 19th ACM Symposium on Document Engineering (DocEng)},
year = {2019},
month = {09},
numpages = {4},
url = {https://doceng.org/doceng2019}
}
Romero, O.; Koci, E.; Lehner, W.; Thiele, M.
To appear in International Conference on Document Analysis and Recognition (ICDAR).2019.
@article{,
author = {Oscar Romero and Elvis Koci and Wolfgang Lehner and Maik Thiele},
title = {A Genetic-based Search for Adaptive Table Recognition in Spreadsheets},
booktitle = {International Conference on Document Analysis and Recognition (ICDAR)},
year = {2019},
month = {09},
numpages = {6},
url = {https://icdar2019.org/},
crossref = {DBLP:conf/icdar/}
}
Romero, O.; Koci, E.; Lehner, W.; Thiele, M.
To appear in International Conference on Document Analysis and Recognition (ICDAR).2019.
@article{,
author = {Oscar Romero and Elvis Koci and Wolfgang Lehner and Maik Thiele},
title = {DECO: A Dataset of Annotated Spreadsheets for Layout and Table Recognition},
booktitle = {International Conference on Document Analysis and Recognition (ICDAR)},
year = {2019},
month = {09},
location = {Sydney, Australia},
numpages = {6},
url = {https://icdar2019.org/},
keywords = {Spreadsheet, Dataset, Enron, Corpus, Annotation, Recognition, Layout, Table, Templates},
crossref = {DBLP:conf/icdar/}
}
Koci, E.; Thiele, M.; Romero, O.; Lehner, W.
In 13th IAPR International Workshop on Document Analysis Systems (DAS).IEEE Computer Society,139-144,2018.Links: https://www.computer.org/csdl/proceedings/das/2018/3346/00/3346a139-abs.html.
@article{,
author = {Elvis Koci and Maik Thiele and Oscar Romero and Wolfgang Lehner},
title = {Table Recognition in Spreadsheets via a Graph Representation},
booktitle = {13th IAPR International Workshop on Document Analysis Systems (DAS)},
year = {2018},
month = {4},
isbn = {978-1-5386-3346-5},
pages = {139--144},
url = {http://doi.ieeecomputersociety.org/10.1109/DAS.2018.48},
publisher = {IEEE Computer Society},
keywords = {Spreadsheet, Table Recognition, Graph Representation, Document Analysis},
crossref = {DBLP:conf/das/2018}
}
Koci, E.; Thiele, M.; Romero, O.; Lehner, W.
In Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2016, Revised Selected Papers.Springer,2018.Links: https://link.springer.com/chapter/10.1007/978-3-319-99701-8_4.
@inbook{,
author = {Elvis Koci and Maik Thiele and Oscar Romero and Wolfgang Lehner},
title = {Cell Classification for Layout Recognition in Spreadsheets},
booktitle = {Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2016, Revised Selected Papers},
series = {Communications in Computer and Information Science},
year = {2018},
publisher = {Springer},
keywords = {Speadsheet, Tabular, Table, Document, Layout, Recognition, Analysis, Classication}
}
Koci, E.; Thiele, M.; Romero, O.; Lehner, W.
In 29th International Conference on Advanced Information Systems Engineering.CAiSE'17, Essen, Germany.Springer,527-541,2017.Links: https://link.springer.com/chapter/10.1007%2F978-3-319-59536-8_33.
@article{,
author = {Elvis Koci and Maik Thiele and Oscar Romero and Wolfgang Lehner},
title = {Table Identification and Reconstruction in Spreadsheets},
booktitle = {29th International Conference on Advanced Information Systems Engineering},
year = {2017},
month = {6},
isbn = {978-3-319-59536-8},
location = {Essen, Germany},
pages = {527--541},
numpages = {15},
url = {https://doi.org/10.1007/978-3-319-59536-8_33},
publisher = {Springer}
}
Koci, E.; Thiele, M.; Lehner, W.
In 8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management.KDIR '16, Porto, Portugal.SCITEPRESS ,77-88,2016.Links: http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006052200770088.
@conference{,
author = {Elvis Koci and Maik Thiele and Wolfgang Lehner},
title = {A Machine Learning Approach for Layout Inference in Spreadsheets},
booktitle = {8th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management},
volume = {1},
year = {2016},
month = {11},
isbn = {978-989-758-203-5},
location = {Porto, Portugal},
pages = {77--88},
numpages = {12},
url = {http://dx.doi.org/10.5220/0006052200770088},
publisher = {SCITEPRESS }
}
Braunschweig, K.; Thiele, M.; Koci, E.; Lehner, W.
KDIR '16, Porto, Portugal.SCITEPRESS ,158-165,2016.Links: http://www.scitepress.org/DigitalLibrary/Link.aspx?doi=10.5220/0006034701580165.
@conference{,
author = {Katrin Braunschweig and Maik Thiele and Elvis Koci and Wolfgang Lehner},
title = {Putting Web Tables into Context},
volume = {1},
year = {2016},
month = {11},
isbn = {978-989-758-203-5},
location = {Porto, Portugal},
pages = {158--165},
numpages = {8},
url = {http://dx.doi.org/10.5220/0006034701580165},
publisher = {SCITEPRESS },
keywords = {Concept Mining, Context Discovery, Information Extraction}
}
Maté, A.; Trujillo, J.; Koci, E.; Zoumpatianos, K.; Mylopoulos, J.
In 19th International Enterprise Distributed Object Computing Conference.IEEE,2015.Links: https://ieeexplore.ieee.org/abstract/document/7321148/.
@conference{,
author = {Alejandro Mat\'{e} and Juan Trujillo and Elvis Koci and Kostas Zoumpatianos and John Mylopoulos},
title = {Monitoring Strategic Business Goals with Argus},
booktitle = {19th International Enterprise Distributed Object Computing Conference},
year = {2015},
month = {9},
location = {Adelaide, SA, Australia},
url = {https://doi.org/10.1109/EDOC.2015.11},
publisher = {IEEE}
}
Analysis and reasoning on spreadsheat references
Michael Hoppe January 1st, 2017 until January 1st, 2017
Supervision: Maik Thiele
Extending Sequential Covering to Fix Misclassifications
Markus Bürger November 1st, 2016 until March 8th, 2017
Supervision: Maik Thiele
Optimal Cell Classification in Spreadsheets
Alexander Volkmann May 23rd, 2017 until August 8th, 2017
Supervision: Maik Thiele
Developing an Excel-Frontend for Extracting Relational Data from Spreadsheet
Ljupka Titizova June 19th, 2017 until September 4th, 2017
Supervision: Maik Thiele
Development of an Excel-frontend for Table Identification in Spreadsheets
Thomas Grosche November 20th, 2017 until March 6th, 2018
Supervision: Maik Thiele
Investigating Graph Partitioning Strategies for Table Identification in Spreadsheets
Jasmin Mohnke January 15th, 2018 until April 2nd, 2018
Supervision: Maik Thiele
Min-Cut Graph Partitioning for Table Identification in Spreadsheets
Michael Günther June 1st, 2017 until September 12th, 2017
Supervision: Maik Thiele
Context-based Layout Inference in Spreadsheets Using LSTM
Dominik Rivoir September 15th, 2017 until April 23rd, 2018
Supervision: Maik Thiele
Active Learning for Spreadsheet Cell Classification
Josephine Rehak October 16th, 2017 until April 16th, 2018
Supervision: Maik Thiele
Clustering Cells in Spreadsheets based on Style and Content Similarities
Anna Elke Brauer October 16th, 2017 until February 5th, 2018
Supervision: Maik Thiele