Publications

2025

1. 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

   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},
   }

2. 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

   @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}},
   }

3. 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 = {https://doi.org/10.1016/j.is.2024.102463},
     author = {Barret, Nelly and Gauquier, Antoine and Law, Jia-Jean and Manolescu, Ioana},
   }

2024

1. 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

   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},
     booktitle = {{Proc.\ {ACM/IEEE} Joint Conference on Digital Libraries, {JCDL} 2024}},
     publisher = {{IEEE}}
   }

2. 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},
   }

3. 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},
   }

4. 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

1. 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 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},
   }

2. 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 = {https://doi.org/10.1007/978-3-031-42914-9_12},
   }

3. 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 = {https://doi.org/10.1007/978-3-031-43458-7_17},
   }

4. 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 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,
   }