Hervé Déjean

82 papers A* 4A 5B 16Journal 32Unranked 24

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Learning Retrieval Models with Sparse Autoencoders. CoRR Thibault Formal, Maxime Louis, Hervé Déjean, Stéphane Clinchant
2026	J	`jnl`	Naver Labs Europe @ WSDM CUP \| Multilingual Retrieval. CoRR Thibault Formal, Maxime Louis, Hervé Déjean, Stéphane Clinchant
2026	J	`jnl`	On the Challenges and Opportunities of Learned Sparse Retrieval for Code. CoRR Simon Lupart, Maxime Louis, Thibault Formal, Hervé Déjean, Stéphane Clinchant
2026	J	`jnl`	Retrieval-Augmented LLM Agents: Learning to Learn from Experience. CoRR Thomas Palmeira Ferraz, Romain Deffayet, Vassilina Nikoulina, Hervé Déjean, Stéphane Clinchant
2025	A	`conf`	Context Embeddings for Efficient Answer Generation in Retrieval-Augmented Generation. WSDM David Rau, Shuai Wang, Hervé Déjean, Stéphane Clinchant, Jaap Kamps
2025	J	`jnl`	OSCAR: Online Soft Compression And Reranking. CoRR Maxime Louis, Thibault Formal, Hervé Déjean, Stéphane Clinchant
2025	—	`conf`	PISCO: Pretty Simple Compression for Retrieval-Augmented Generation. ACL (Findings) Maxime Louis, Hervé Déjean, Stéphane Clinchant
2025	J	`jnl`	PISCO: Pretty Simple Compression for Retrieval-Augmented Generation. CoRR Maxime Louis, Hervé Déjean, Stéphane Clinchant
2025	J	`jnl`	RANa: Retrieval-Augmented Navigation. CoRR Gianluca Monaci, Rafael S. Rezende, Romain Deffayet, Gabriela Csurka, Guillaume Bono, Hervé Déjean, Stéphane Clinchant, Christian Wolf
2025	J	`jnl`	RANa: Retrieval-Augmented Navigation. Trans. Mach. Learn. Res. Gianluca Monaci, Rafael S. Rezende, Romain Deffayet, Gabriela Csurka, Guillaume Bono, Hervé Déjean, Stéphane Clinchant, Christian Wolf
2025	J	`jnl`	Reranking with Compressed Document Representation. CoRR Hervé Déjean, Stéphane Clinchant
2024	J	`jnl`	A Thorough Comparison of Cross-Encoders and LLMs for Reranking SPLADE. CoRR Hervé Déjean, Stéphane Clinchant, Thibault Formal
2024	—	`conf`	BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. EMNLP (Findings) David Rau, Hervé Déjean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Stéphane Clinchant, Vassilina Nikoulina
2024	J	`jnl`	BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. CoRR David Rau, Hervé Déjean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Vassilina Nikoulina, Stéphane Clinchant
2024	J	`jnl`	Context Embeddings for Efficient Answer Generation in RAG. CoRR David Rau, Shuai Wang, Hervé Déjean, Stéphane Clinchant
2024	J	`jnl`	Let your LLM generate a few tokens and you will reduce the need for retrieval. CoRR Hervé Déjean
2024	J	`jnl`	Retrieval-augmented generation in multilingual settings. CoRR Nadezhda Chirkova, David Rau, Hervé Déjean, Thibault Formal, Stéphane Clinchant, Vassilina Nikoulina
2024	J	`jnl`	SPLADE-v3: New baselines for SPLADE. CoRR Carlos Lassance, Hervé Déjean, Thibault Formal, Stéphane Clinchant
2024	A*	`conf`	SPLATE: Sparse Late Interaction Retrieval. SIGIR Thibault Formal, Stéphane Clinchant, Hervé Déjean, Carlos Lassance
2024	J	`jnl`	SPLATE: Sparse Late Interaction Retrieval. CoRR Thibault Formal, Stéphane Clinchant, Hervé Déjean, Carlos Lassance
2024	—	`conf`	Two-Step SPLADE: Simple, Efficient and Effective Approximation of SPLADE. ECIR (2) Carlos Lassance, Hervé Déjean, Stéphane Clinchant, Nicola Tonellotto
2024	J	`jnl`	Two-Step SPLADE: Simple, Efficient and Effective Approximation of SPLADE. CoRR Carlos Lassance, Hervé Déjean, Stéphane Clinchant, Nicola Tonellotto
2023	A*	`conf`	A Static Pruning Study on Sparse Neural Retrievers. SIGIR Carlos Lassance, Simon Lupart, Hervé Déjean, Stéphane Clinchant, Nicola Tonellotto
2023	J	`jnl`	A Static Pruning Study on Sparse Neural Retrievers. CoRR Carlos Lassance, Simon Lupart, Hervé Déjean, Stéphane Clinchant, Nicola Tonellotto
2023	—	`conf`	An Experimental Study on Pretraining Transformers from Scratch for IR. ECIR (1) Carlos Lassance, Hervé Déjean, Stéphane Clinchant
2023	J	`jnl`	An Experimental Study on Pretraining Transformers from Scratch for IR. CoRR Carlos Lassance, Hervé Déjean, Stéphane Clinchant
2023	A*	`conf`	Benchmarking Middle-Trained Language Models for Neural Search. SIGIR Hervé Déjean, Stéphane Clinchant, Carlos Lassance, Simon Lupart, Thibault Formal
2023	J	`jnl`	Benchmarking Middle-Trained Language Models for Neural Search. CoRR Hervé Déjean, Stéphane Clinchant, Carlos Lassance, Simon Lupart, Thibault Formal
2023	—	`conf`	Parameter-Efficient Sparse Retrievers and Rerankers Using Adapters. ECIR (2) Vaishali Pal, Carlos Lassance, Hervé Déjean, Stéphane Clinchant
2023	J	`jnl`	Parameter-Efficient Sparse Retrievers and Rerankers using Adapters. CoRR Vaishali Pal, Carlos Lassance, Hervé Déjean, Stéphane Clinchant
2022	J	`jnl`	LayoutXLM vs. GNN: An Empirical Evaluation of Relation Extraction for Documents. CoRR Hervé Déjean, Stéphane Clinchant, Jean-Luc Meunier
2019	J	`jnl`	Comparing Machine Learning Approaches for Table Recognition in Historical Register Books. CoRR Stéphane Clinchant, Hervé Déjean, Jean-Luc Meunier, Eva Maria Lang, Florian Kleber
2019	A	`conf`	ICDAR 2019 Competition on Table Detection and Recognition (cTDaR). ICDAR Liangcai Gao, Yilun Huang, Hervé Déjean, Jean-Luc Meunier, Qinqin Yan, Yu Fang, Florian Kleber, Eva Maria Lang
2019	A	`conf`	Table Rows Segmentation. ICDAR Hervé Déjean, Jean-Luc Meunier
2019	J	`jnl`	Transforming scholarship in the archives through handwritten text recognition. J. Documentation Günter Mühlberger, Louise Seaward, Melissa Terras, Sofia Ares Oliveira, Vicente Bosch, Maximilian Bryan, Sebastian Colutto, Hervé Déjean, Markus Diem, Stefan Fiel, Basilis Gatos, Albert Greinoecker, Tobias Grüning, Günter Hackl, Vili Haukkovaara, Gerhard Heyer, Lauri Hirvonen, Tobias Hodel, Matti Jokinen, Philip Kahle, Mario Kallio, Frédéric Kaplan, Florian Kleber, Roger Labahn, Eva Maria Lang, Sören Laube, Gundram Leifert, Georgios Louloudis, Rory McNicholl, Jean-Luc Meunier, Johannes Michael, Elena Mühlbauer, Nathanael Philipp, Ioannis Pratikakis, Joan Puigcerver Pérez, Hannelore Putz, George Retsinas, Verónica Romero, Robert Sablatnig, Joan-Andreu Sánchez, Philip Schofield, Giorgos Sfikas, Christian Sieber, Nikolaos Stamatopoulos, Tobias Strauß, Tamara Terbul, Alejandro H. Toselli, Berthold Ulreich, Mauricio Villegas, Enrique Vidal, Johanna Walcher, Max Weidemann, Herbert Wurster, Konstantinos Zagoris
2019	A	`conf`	Versatile Layout Understanding via Conjugate Graph. ICDAR Animesh Prasad, Hervé Déjean, Jean-Luc Meunier
2018	J	`jnl`	Bench-Marking Information Extraction in Semi-Structured Historical Handwritten Records. CoRR Animesh Prasad, Hervé Déjean, Jean-Luc Meunier, Max Weidemann, Johannes Michael, Gundram Leifert
2018	B	`conf`	Comparing Machine Learning Approaches for Table Recognition in Historical Register Books. DAS Stéphane Clinchant, Hervé Déjean, Jean-Luc Meunier, Eva Maria Lang, Florian Kleber
2018	B	`conf`	Matching Table Structures of Historical Register Books using Association Graphs. ICFHR Florian Kleber, Markus Diem, Hervé Déjean, Jean-Luc Meunier, Eva Maria Lang
2015	A	`conf`	Extracting structured data from unstructured document with incomplete resources. ICDAR Hervé Déjean
2014	—	`conf`	Using ancestral layout models for document digitization. DATeCH Hervé Déjean
2011	—	`conf`	Unsupervised method to generate page templates. DRR Hervé Déjean
2011	—	`conf`	Using Page Breaks for Book Structuring. INEX Hervé Déjean
2011	—	`conf`	XML Processing in the Cloud: Large-Scale Digital Preservation in Small Institutions. IPDPS Workshops Peter Wittek, Thierry Jacquin, Hervé Déjean, Jean-Pierre Chanod, Sándor Darányi
2010	—	`conf`	Document: a useful level for facing noisy data. AND Hervé Déjean, Jean-Luc Meunier
2010	—	`conf`	Numbered sequence detection in documents. DRR Hervé Déjean
2010	—	`conf`	Preserving the Intent behind. Automation in Digital Preservation Thierry Jacquin, Hervé Déjean, Jean-Pierre Chanod
2010	B	`conf`	Reflections on the INEX structure extraction competition. Document Analysis Systems Hervé Déjean, Jean-Luc Meunier
2010	—	`conf`	Xeproc(c): A Model-Based Approach towards Document Process Preservation. ECDL Thierry Jacquin, Hervé Déjean, Jean-Pierre Chanod
2010	J	`jnl`	Xerox Launches Document Process Modelling Technology 'Xeproc©'. ERCIM News Thierry Jacquin, Hervé Déjean, Jean-Pierre Chanod
2009	J	`jnl`	On tables of contents and how to recognize them. Int. J. Document Anal. Recognit. Hervé Déjean, Jean-Luc Meunier
2009	—	`conf`	XRCE Participation to the 2009 Book Structure Task. INEX Hervé Déjean, Jean-Luc Meunier
2008	B	`conf`	Combining Multiple Methods for Book Indexing. Document Analysis Systems Hervé Déjean, Jean-Luc Meunier
2008	—	`conf`	Versatile page numbering analysis. DRR Hervé Déjean, Jean-Luc Meunier
2008	—	`conf`	XRCE Participation to the Book Structure Task. INEX Hervé Déjean, Jean-Luc Meunier
2007	B	`conf`	Logical document conversion: combining functional and formal knowledge. ACM Symposium on Document Engineering Hervé Déjean, Jean-Luc Meunier
2006	B	`conf`	A System for Converting PDF Documents into Structured XML Format. Document Analysis Systems Hervé Déjean, Jean-Luc Meunier
2005	J	`jnl`	Automatic processing of multilingual medical terminology: applications to thesaurus enrichment and cross-language information retrieval. Artif. Intell. Medicine Hervé Déjean, Éric Gaussier, Jean-Michel Renders, Fatiha Sadat
2005	—	`conf`	From Legacy Documents to XML: A Conversion Framework. ECDL Jean-Pierre Chanod, Boris Chidlovskii, Hervé Déjean, Olivier Fambon, Jérôme Fuselier, Thierry Jacquin, Jean-Luc Meunier
2005	B	`conf`	Structuring documents according to their table of contents. ACM Symposium on Document Engineering Hervé Déjean, Jean-Luc Meunier
2004	A*	`conf`	A Geometric View on Bilingual Lexicon Extraction from Comparable Corpora. ACL Éric Gaussier, Jean-Michel Renders, Irina Matveeva, Cyril Goutte, Hervé Déjean
2003	—	`conf`	Reducing Parameter Space for Word Alignment. ParallelTexts@NAACL-HLT Hervé Déjean, Éric Gaussier, Cyril Goutte, Kenji Yamada
2003	—	`conf`	Report on CLEF-2003 Experiments: Two Ways of Extracting Multilingual Resources from Corpora. CLEF Nicola Cancedda, Hervé Déjean, Éric Gaussier, Jean-Michel Renders, Alexei Vinokourov
2003	—	`conf`	Report on CLEF-2003 Experiments: Two Ways of Extracting Multilingual Resources from Corpora. CLEF (Working Notes) Nicola Cancedda, Hervé Déjean, Éric Gaussier, Jean-Michel Renders, Alexei Vinokourov
2002	B	`conf`	An Approach Based on Multilingual Thesauri and Model Combination for Bilingual Lexicon Extraction. COLING Hervé Déjean, Éric Gaussier, Fatiha Sadat
2002	—	`conf`	Assessing Automatically Extracted Bilingual Lexicons for CLIR in Vertical Domains: XRCE Participation in the GIRT Track of CLEF 2002. CLEF Jean-Michel Renders, Hervé Déjean, Éric Gaussier
2002	B	`conf`	Combining Labelled and Unlabelled Data: A Case Study on Fisher Kernels and Transductive Inference for Biological Entity Recognition. CoNLL Cyril Goutte, Hervé Déjean, Éric Gaussier, Nicola Cancedda, Jean-Michel Renders
2002	J	`jnl`	Learning Rules and Their Exceptions. J. Mach. Learn. Res. Hervé Déjean
2002	—	`conf`	XRCE Participation in CLEF 2002. CLEF (Working Notes) Jean-Michel Renders, Hervé Déjean, Éric Gaussier
2001	J	`jnl`	Introduction to the CoNLL-2001 Shared Task: Clause Identification CoRR Erik F. Tjong Kim Sang, Hervé Déjean
2001	B	`conf`	Introduction to the CoNLL-2001 shared task: clause identification. CoNLL Erik F. Tjong Kim Sang, Hervé Déjean
2001	J	`jnl`	Learning Computational Grammars CoRR John Nerbonne, Anja Belz, Nicola Cancedda, Hervé Déjean, James Alistair Hammerton, Rob Koeling, Stasinos Konstantopoulos, Miles Osborne, Franck Thollard, Erik F. Tjong Kim Sang
2001	B	`conf`	Learning Computational Grammars. CoNLL John Nerbonne, Anja Belz, Nicola Cancedda, Hervé Déjean, James Alistair Hammerton, Rob Koeling, Stasinos Konstantopoulos, Miles Osborne, Franck Thollard, Erik F. Tjong Kim Sang
2001	B	`conf`	Using ALLiS for clausing. CoNLL Hervé Déjean
2000	—	`conf`	ALLiS: a Symbolic Learning System for Natural Language Learning. CoNLL/LLL Hervé Déjean
2000	J	`jnl`	Applying System Combination to Base Noun Phrase Identification CoRR Erik F. Tjong Kim Sang, Walter Daelemans, Hervé Déjean, Rob Koeling, Yuval Krymolowski, Vasin Punyakanok, Dan Roth
2000	B	`conf`	Applying System Combination to Base Noun Phrase Identification. COLING Erik F. Tjong Kim Sang, Walter Daelemans, Hervé Déjean, Rob Koeling, Yuval Krymolowski, Vasin Punyakanok, Dan Roth
2000	B	`conf`	How To Evaluate and Compare Tagsets? A Proposal. LREC Hervé Déjean
2000	—	`conf`	Learning Syntactic Structures with XML. CoNLL/LLL Hervé Déjean
2000	B	`conf`	Theory Refinement and Natural Language Learning. COLING Hervé Déjean
1998	—	`—`	Concepts et algorithmes pour la découverte des structures formelles des langues. (Concepts and Algorithms for Discovering Formal Structures of Languages). Hervé Déjean
1998	B	`conf`	Morphemes as Necessary Concept for Structures Discovery from Untagged Corpora. CoNLL Hervé Déjean