Publications | Antoine Gauquier

Research papers (conferences or journals) Demonstration papers Workshop papers Posters Miscellaneous

2026

Ph.D. Thesis

Efficient and Scalable Methods for the Acquisition, Retrieval, and Understanding of Open Tabular Data

Antoine Gauquier

École normale supérieure, PSL University, Sep 2026

Defended on September 23, 2026

Bib PDF Slides

@phdthesis{gauquier2026thesis,
  title = {{Efficient and Scalable Methods for the Acquisition, Retrieval, and Understanding of Open Tabular Data}},
  author = {Gauquier, Antoine},
  school = {{École normale supérieure, PSL University}},
  month = sep,
  year = {2026},
  note = {Defended on September 23, 2026}
}

CIKM

Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges

Antoine Gauquier, Ioana Manolescu, and Pierre Senellart

In Proc. of the 35th International ACM Conference on Knowledge and Information Management, CIKM 2026, Nov 2026

DOI Bib PDF Code and Data

@inproceedings{gauquier2026structured,
  title = {{Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges}},
  author = {Gauquier, Antoine and Manolescu, Ioana and Senellart, Pierre},
  booktitle = {Proc.\ of the 35th International {ACM} Conference on Knowledge and Information Management, {CIKM} 2026},
  address = {Rome, Italy},
  month = nov,
  year = {2026},
  doi = {10.1145/3799682.3840907},
}

ArXiv

Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)

Antoine Gauquier, Ioana Manolescu, and Pierre Senellart

Aug 2026

arXiv Bib PDF Code and Data

@misc{gauquier2026structuredextended,
  title = {{Structured Prediction for Scalable Spreadsheet Table Understanding: From Cell Types to Table Ranges (Extended Version)}},
  author = {Gauquier, Antoine and Manolescu, Ioana and Senellart, Pierre},
  month = aug,
  year = {2026},
  eprint = {2608.16050},
  archiveprefix = {arXiv},
}

TLDKS

STAR: Efficient, Scalable, and Modular Retrieval of Statistical Tables

Antoine Gauquier, Simon Ebel, Helena Galhardas, and 4 more authors

Transactions on Large-Scale Data- and Knowledge-Centered Systems (TLDKS), Jun 2026

Bib PDF Code Data Experiments

@article{gauquier2026star,
  title = {{STAR: Efficient, Scalable, and Modular Retrieval of Statistical Tables}},
  author = {Gauquier, Antoine and Ebel, Simon and Galhardas, Helena and Galizzi, Th\'eo and Manolescu, Ioana and Peden, Aurélien and Senellart, Pierre},
  journal = {Transactions on Large-Scale Data- and Knowledge-Centered Systems (TLDKS)},
  month = jun,
  year = {2026},
}

ICDE

Efficient and Scalable Search for Statistics

Antoine Gauquier, Simon Ebel, Helena Galhardas, and 4 more authors

In Proc. of the 42nd IEEE International Conference on Data Engineering, ICDE 2026, May 2026

DOI Bib PDF Code Data Experiments Poster Slides

@inproceedings{gauquier2026efficientandscalable,
  title = {{Efficient and Scalable Search for Statistics}},
  author = {Gauquier, Antoine and Ebel, Simon and Galhardas, Helena and Galizzi, Th\'eo and Manolescu, Ioana and Peden, Aurélien and Senellart, Pierre},
  booktitle = {Proc.\ of the 42nd {IEEE} International Conference on Data Engineering, {ICDE} 2026},
  address = {Montr\'eal, Canada},
  month = may,
  year = {2026},
  doi = {10.1109/icde65706.2026.00088},
}

EDBT

Efficient Crawling for Scalable Web Data Acquisition

Antoine Gauquier, Ioana Manolescu, and Pierre Senellart

In Proc. of the 29th International Conference on Extending Database Technology, EDBT 2026, Mar 2026

DOI Bib PDF Code Slides

@inproceedings{gauquier2026efficientcrawling,
  title = {{Efficient Crawling for Scalable Web Data Acquisition}},
  author = {Gauquier, Antoine and Manolescu, Ioana and Senellart, Pierre},
  booktitle = {Proc.\ of the 29th International Conference on Extending Database Technology, {EDBT} 2026},
  address = {Tampere, Finland},
  month = mar,
  year = {2026},
  doi = {10.48786/edbt.2026.30},
}

ArXiv

Efficient Crawling for Scalable Web Data Acquisition (Extended Version)

Antoine Gauquier, Ioana Manolescu, and Pierre Senellart

Feb 2026

arXiv Bib PDF Code

@misc{gauquier2026efficientcrawlingextended,
  title = {{Efficient Crawling for Scalable Web Data Acquisition (Extended Version)}},
  author = {Gauquier, Antoine and Manolescu, Ioana and Senellart, Pierre},
  month = feb,
  year = {2026},
  eprint = {2602.11874},
  archiveprefix = {arXiv},
}

2025

ECSQARU

Expected Shapley Value is Shapley Value for Expected Utility Game

Pratik Karmakar, Antoine Gauquier, and Pierre Senellart

In Proc. of the 18th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, ECSQARU 2025, Sep 2025

DOI Bib PDF Slides

@inproceedings{karmakar2025expected,
  title = {{Expected Shapley Value is Shapley Value for Expected Utility Game}},
  author = {Karmakar, Pratik and Gauquier, Antoine and Senellart, Pierre},
  booktitle = {Proc.\ of the 18th European Conference on
  Symbolic and Quantitative Approaches to Reasoning with Uncertainty, {ECSQARU} 2025},
  address = {Hagen, Germany},
  month = sep,
  year = {2025},
  doi = {10.1007/978-3-032-05134-9_16},
}

ECIR

TheoremView: A Framework for Extracting Theorem-Like Environments from Raw PDFs

Shrey Mishra, Neil Sharma, Antoine Gauquier, and 1 more author

In Proc. of the 47th European Conference on Information Retrieval, ECIR 2025, Apr 2025

DOI Bib PDF

@inproceedings{mishra2025theoremview,
  title = {{TheoremView: A Framework for Extracting Theorem-Like Environments from Raw PDFs}},
  author = {Mishra, Shrey and Sharma, Neil and Gauquier, Antoine and Senellart, Pierre},
  booktitle = {Proc.\ of the 47th European Conference on Information Retrieval, {ECIR} 2025},
  address = {Lucca, Italy},
  month = apr,
  year = {2025},
  doi = {10.1007/978-3-031-88720-8_5},
}

EGC

Apprentissage multimodal modulaire pour l’extraction de théorèmes et de preuves dans des documents scientifiques longs

Shrey Mishra, Antoine Gauquier, and Pierre Senellart

In Proc. Extraction et Gestion des Connaissances, EGC 2025, Jan 2025

Bib PDF Poster

@inproceedings{mishra2025apprentissage,
  title = {{Apprentissage multimodal modulaire pour l'extraction de th\'eor\`emes et de preuves dans des documents scientifiques longs}},
  author = {Mishra, Shrey and Gauquier, Antoine and Senellart, Pierre},
  booktitle = {{Proc.\ Extraction et Gestion des Connaissances, {EGC} 2025}},
  address = {Strasbourg, France},
  month = jan,
  year = {2025},
  publisher = {{RNTI}},
}

Inf. Sys.

Finding meaningful paths in heterogeneous graphs with PathWays

Nelly Barret, Antoine Gauquier, Jia-Jean Law, and 1 more author

Information Systems, Jan 2025

DOI Bib PDF

@article{barret2025finding,
  title = {Finding meaningful paths in heterogeneous graphs with PathWays},
  journal = {Information Systems},
  volume = {127},
  pages = {102463},
  year = {2025},
  month = jan,
  issn = {0306-4379},
  doi = {10.1016/j.is.2024.102463},
  author = {Barret, Nelly and Gauquier, Antoine and Law, Jia-Jean and Manolescu, Ioana},
}

2024

JCDL

Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents

Shrey Mishra, Antoine Gauquier, and Pierre Senellart

In Proc. ACM/IEEE Joint Conference on Digital Libraries, JCDL 2024, Dec 2024

DOI Bib PDF

@inproceedings{mishra2024modular,
  title = {{Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents}},
  author = {Mishra, Shrey and Gauquier, Antoine and Senellart, Pierre},
  year = {2024},
  month = dec,
  address = {Hong Kong, China},
  doi = {10.1145/3677389.3702540},
  booktitle = {{Proc.\ {ACM/IEEE} Joint Conference on Digital Libraries, {JCDL} 2024}},
  publisher = {{IEEE}}
}

ArXiv

Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)

Shrey Mishra, Antoine Gauquier, and Pierre Senellart

Dec 2024

arXiv Bib PDF

@misc{mishra2024modularextended,
  title = {Modular Multimodal Machine Learning for Extraction of Theorems and Proofs in Long Scientific Documents (Extended Version)},
  author = {Mishra, Shrey and Gauquier, Antoine and Senellart, Pierre},
  year = {2024},
  eprint = {2307.09047},
  archiveprefix = {arXiv},
}

SDP

First Steps in Building a Knowledge Base of Mathematical Results

Shrey Mishra, Yacine Brihmouche, Théo Delemazure, and 2 more authors

In Proc. of the Fourth Workshop on Scholarly Document Processing (SDP 2024), Aug 2024

Bib PDF

@inproceedings{mishra2024first,
  title = {First Steps in Building a Knowledge Base of Mathematical Results},
  author = {Mishra, Shrey and Brihmouche, Yacine and Delemazure, Th\'eo and Gauquier, Antoine and Senellart, Pierre},
  booktitle = {{Proc.\ of the Fourth Workshop on Scholarly Document Processing (SDP 2024)}},
  month = aug,
  year = {2024},
  address = {Bangkok, Thailand},
  publisher = {Association for Computational Linguistics},
  url = {https://aclanthology.org/2024.sdp-1.16/},
  pages = {165--174},
}

VLDB Ph.D.

Towards Efficient Construction of a Traceable, Multimodal, and Heterogeneous Data Warehouse

Antoine Gauquier

In Proc. of VLDB 2024 PhD Workshop-The 50th International Conference on Very Large Data Bases, Aug 2024

Bib PDF Slides

@inproceedings{gauquier2024towards,
  title = {Towards Efficient Construction of a Traceable, Multimodal, and Heterogeneous Data Warehouse},
  author = {Gauquier, Antoine},
  booktitle = {{Proc.\ of VLDB 2024 PhD Workshop-The 50th International Conference on Very Large Data Bases}},
  address = {Guangzhou, China},
  year = {2024},
  month = aug,
  url = {https://vldb.org/2024/?accepted-phd-workshop-papers},
}

2023

Doc. Eng.

Automatically Inferring the Document Class of a Scientific Article

Antoine Gauquier, and Pierre Senellart

In Proc. of the ACM Symposium on Document Engineering 2023, Aug 2023

Runner-up for Best Paper Award DOI Bib PDF Code and Models Slides

Runner-up for Best Paper Award at Doc.Eng. 2023 conference

@inproceedings{gauquier2023automatically,
  author = {Gauquier, Antoine and Senellart, Pierre},
  title = {Automatically Inferring the Document Class of a Scientific Article},
  year = {2023},
  month = aug,
  isbn = {9798400700279},
  doi = {10.1145/3573128.3604894},
  publisher = {Association for Computing Machinery},
  booktitle = {{Proc.\ of the ACM Symposium on Document Engineering 2023}},
  articleno = {11},
  numpages = {10},
  address = {Limerick, Ireland},
  series = {DocEng '23},
}

ADBIS

Exploring Heterogeneous Data Graphs Through Their Entity Paths

Nelly Barret, Antoine Gauquier, Jia-Jean Law, and 1 more author

In Proc. of Advances in Databases and Information Systems, Sep 2023

DOI Bib PDF

@inproceedings{barret2023exploring,
  author = {Barret, Nelly and Gauquier, Antoine and Law, Jia-Jean and Manolescu, Ioana},
  title = {Exploring Heterogeneous Data Graphs Through Their Entity Paths},
  booktitle = {{Proc.\ of Advances in Databases and Information Systems}},
  year = {2023},
  month = sep,
  publisher = {Springer},
  address = {Barcelona, Spain},
  pages = {163--179},
  isbn = {978-3-031-42914-9},
  doi = {10.1007/978-3-031-42914-9_12},
}

ESWC

PathWays: Entity-Focused Exploration of Heterogeneous Data Graphs

Nelly Barret, Antoine Gauquier, Jia-Jean Law, and 1 more author

In Proc. of the Semantic Web: ESWC 2023 Satellite Events, May 2023

DOI Bib PDF

@inproceedings{barret2023pathways,
  author = {Barret, Nelly and Gauquier, Antoine and Law, Jia-Jean and Manolescu, Ioana},
  title = {PathWays: Entity-Focused Exploration of Heterogeneous Data Graphs},
  booktitle = {{Proc.\ of the Semantic Web: ESWC 2023 Satellite Events}},
  year = {2023},
  month = may,
  publisher = {Springer},
  address = {Hersonissos, Crete, Greece},
  pages = {91--95},
  isbn = {978-3-031-43458-7},
  doi = {10.1007/978-3-031-43458-7_17},
}

Msc. Thesis

Impact of the document class in the automatic extraction of mathematical environments in the scientific literature

Antoine Gauquier

IMT Nord Europe and École normale supérieure, Jul 2023

Bib PDF Code and Models Slides

@mastersthesis{gauquier2023impact,
  title = {Impact of the document class in the automatic extraction of mathematical environments in the scientific literature},
  author = {Gauquier, Antoine},
  pages = {44},
  school = {IMT Nord Europe and École normale supérieure},
  year = {2023},
  month = jul,
}

2022

Msc. Thesis

Path-based ConnectionLens graph exploration

Antoine Gauquier

IMT Nord Europe and Inria, Aug 2022

Bib PDF

@mastersthesis{gauquier2022path,
  title = {Path-based ConnectionLens graph exploration},
  author = {Gauquier, Antoine},
  pages = {37},
  school = {IMT Nord Europe and Inria},
  year = {2022},
  month = aug,
}