Benjamin Piwowarski
Publications
Publications
|
|
Structural Deep Encoding for Table Question AnsweringThe 63rd Annual Meeting of the Association for Computational Linguistics, ACL, Jul 2025, Vienna, Austria. pp.2389-2402, ⟨10.18653/v1/2025.findings-acl.121⟩ |
|
|
Understanding Matching Mechanisms in Cross-EncodersWorkshop on Explainability in Information Retrieval, Jul 2025, Padova, Italy, Italy |
|
|
Comprendre la Nature des Signaux de Correspondance dans les Modèles Neuronaux pour la RIConférence en Recherche d’Information et Applications, Association francophone de Recherche d’Information et Applications, Jun 2025, Marseille, France |
|
|
Towards Lossless Token Pruning in Late-Interaction Retrieval ModelsThe 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2025, Padoue, Italy. pp.2407-2417, ⟨10.1145/3726302.3730100⟩ |
|
|
Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse RetrievalThe 48th International ACM SIGIR Conference on Research and Development in Information Retrieval, ACM, Jul 2025, Padova, France. ⟨10.1145/3726302.3730239⟩ |
|
|
Mixture of Languages: Improved Multilingual Encoders Through Language GroupingProceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Nov 2025, Suzhou, China. pp.29695-29710, ⟨10.18653/v1/2025.emnlp-main.1509⟩ |
|
|
Comment mesurer les biais politiques des grands modèles de langue multilingues?20e Conférence en Recherche d’Information et Applications (CORIA) 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN) 27ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL) Les 18e Rencontres Jeunes Chercheurs en RI (RJCRI), 2025, Marseille, France. pp.1-7 |
|
|
Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge ConflictsFindings of the Association for Computational Linguistics: EMNLP 2025, Nov 2025, Suzhou, China. pp.20469-20481, ⟨10.18653/v1/2025.findings-emnlp.1116⟩ |
|
|
On the Representations of Entities in Auto-regressive Large Language Models8th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, Nov 2025, Suzhou, China. pp.433-451, ⟨10.18653/v1/2025.blackboxnlp-1.25⟩ |
|
|
Which Neurons Matter in IR? Applying Integrated Gradients-based Methods to Understand Cross-EncodersICTIR '24: The 2024 ACM SIGIR International Conference on the Theory of Information Retrieval, Jul 2024, Washington DC, United States. pp.133-143, ⟨10.1145/3664190.3672528⟩ |
|
|
Simple Domain Adaptation for Sparse Retrievers46th European Conference on Information Retrieval, Mar 2024, Glasgow, United Kingdom. pp.403-412, ⟨10.1007/978-3-031-56063-7_32⟩ |
|
|
Learning Reading Order via Document Layout with Layout2PosLinking Theory and Practice of Digital Libraries, Sep 2024, Ljubbljana, Slovenia. pp.3-19, ⟨10.1007/978-3-031-72437-4_1⟩ |
|
|
Structured representation for Information RetrievalCOnférence en Recherche d'Informations et Applications, Apr 2024, La Rochelle, France. ⟨10.24348/coria.2024.abstract_24⟩ |
|
|
Learning Relational Decomposition of Queries for Question Answering from Tables62nd Annual Meeting of the Association for Computational Linguistics, Aug 2024, Bangkok, Thailand. pp.10471--10485 |
|
|
MEXMA: Token-level objectives improve sentence representations63rd Annual Meeting of the Association for Computational Linguistics, Jul 2025, Vienna, Austria |
|
|
What Makes Multimodal In-Context Learning Work?2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Jun 2024, Seattle, United States. pp.1539-1550, ⟨10.1109/CVPRW63382.2024.00161⟩ |
|
|
Towards Query Performance Prediction for Neural Information Retrieval: Challenges and OpportunitiesICTIR '23: The 2023 ACM SIGIR International Conference on the Theory of Information Retrieval, Jul 2023, Taipei Taiwan, Taiwan. pp.51-63, ⟨10.1145/3578337.3605142⟩ |
|
|
CoSPLADE : Adaptation d'un Modèle Neuronal Basé sur des Représentations Parcimonieuses pour la Recherche d'Information ConversationnelleCORIA-TALN 2023 18e Conférence en Recherche d'Information et Applications (CORIA), Jun 2023, Paris, France. pp.207-212 |
|
|
CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval45th European Conference on Information Retrieval (ECIR 2023), Apr 2023, Dublin, Ireland. pp.537-552, ⟨10.1007/978-3-031-28244-7_34⟩ |
|
|
Query Performance Prediction for Neural IR: Are We There Yet?European Conference on Information Retrieval, Apr 2023, Dublin (Ireland), Ireland. pp.232-248, ⟨10.1007/978-3-031-28244-7_15⟩ |
|
|
LoRaLay: A Multilingual and Multimodal Dataset for Long Range and Layout-Aware SummarizationThe 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2023), May 2023, Dubrovnik, Croatia |
|
|
XPMIR: Une bibliothèque modulaire pour l'apprentissage d'ordonnancement et les expériences de RI neuronale18e Conférence en Recherche d'Information et Applications -- 16e Rencontres Jeunes Chercheurs en RI -- 30e Conférence sur le Traitement Automatique des Langues Naturelles -- 25e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues, 2023, Paris, France. pp.222-233 |
|
|
LoRaLay: A Multilingual and Multimodal Dataset for Long Range and Layout-Aware SummarizationProceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, May 2023, Dubrovnik, Croatia. pp.636-651, ⟨10.18653/v1/2023.eacl-main.46⟩ |
|
|
Generative Cooperative Networks for Natural Language GenerationICML 2022 - 39th International Conference on Machine Learning, Jul 2022, Baltimore, MD, United States. pp.11891--11905 |
|
|
From Distillation to Hard Negative SamplingSIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2022, Madrid, Spain. pp.2353-2359, ⟨10.1145/3477495.3531857⟩ |
|
|
Which Discriminator for Cooperative Text Generation?SIGIR 2022 - 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2022, Madrid, Spain. pp.2360-2365, ⟨10.1145/3477495.3531858⟩ |
|
|
Choisir le bon co-équipier pour la génération coopérative de texteTALN 2022 - 29e conférence sur le Traitement Automatique des Langues Naturelles, Jun 2022, Avignon, France. pp.12-26 |
|
|
Match Your Words! A Study of Lexical Matching in Neural Information RetrievalEuropean Conference on Information Retrieval, Apr 2022, Stavenger, Norway. pp.120-127, ⟨10.1007/978-3-030-99739-7_14⟩ |
|
|
Une Analyse du Modèle ColBERTConférence en Recherche d’Information et Applications, Apr 2021, Grenoble (virtuelle), France |
|
|
A White Box Analysis of ColBERT43rd EUROPEAN CONFERENCE ON INFORMATION RETRIEVAL, Mar 2021, Lucca (online), Italy. pp.257-263, ⟨10.1007/978-3-030-72240-1_23⟩ |
|
|
To Beam Or Not To Beam: That is a Question of Cooperation for Language GANsAdvances in Neural Information Processing Systems, Dec 2021, Virtual, United States. pp.26585--26597 |
|
|
QuestEval: Summarization Asks for Fact-based EvaluationProceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Nov 2021, Punta Cana (en ligne), Dominican Republic. pp.6594-6604, ⟨10.18653/v1/2021.emnlp-main.529⟩ |
|
|
SPLADE: Sparse Lexical and Expansion Model for First Stage RankingSIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2021, Virtual Event, Canada. pp.2288-2292, ⟨10.1145/3404835.3463098⟩ |
|
|
Skim-Attention: Learning to Focus via Document LayoutFindings of the 2021 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP 2021), Nov 2021, Punta Cana, Dominican Republic |
|
|
ColdGANs: Taming Language GANs with Cautious Sampling StrategiesAdvances in Neural Information Processing Systems, Dec 2020, Virtual, Åland Islands. pp.18978-18989 |
|
|
Experimaestro and DatamaestroSIGIR '20: The 43rd International ACM SIGIR conference on research and development in Information Retrieval, Jul 2020, Virtual Event China, China. pp.2173-2176, ⟨10.1145/3397271.3401410⟩ |
|
|
Using BERT and BART for Query SuggestionJoint Conference of the Information Retrieval Communities in Europe, Jul 2020, Samatan, France |
|
|
Discriminative Adversarial Search for Abstractive Summarization37th International Conference on Machine Learning, Jul 2020, Virtual, Åland Islands. pp.8555-8564 |
|
|
Answers Unite! Unsupervised Metrics for Reinforced Summarization Models2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Nov 2019, Hong Kong, China. pp.3237-3247, ⟨10.18653/v1/D19-1320⟩ |
Self-Attention Architectures for Answer-Agnostic Neural Question GenerationACL 2019 - Annual Meeting of the Association for Computational Linguistics, Jul 2019, Florence, Italy. pp.6027-6032, ⟨10.18653/v1/P19-1604⟩ |
|
Extraction d'information non supervisée avec des modèles discriminantsCAp 2019 - 21ème Conférence sur l'Apprentissage automatique, Jul 2019, Toulouse, France |
|
Architecture basée sur les mécanismes d'attention: le cas de la génération de questions neuronalesCOnférence en Recherche d'Informations et Applications - CORIA 2019, 16th French Information Retrieval Conference, May 2019, Lyon, France. ⟨10.24348/coria.2019.CORIA_2019_paper_11⟩ |
|
Un modèle multimodal d’apprentissage de représentations de phrases qui préserve la sémantique visuelleCOnférence en Recherche d'Informations et Applications, May 2019, Lyon, France. ⟨10.24348/coria.2019.CORIA_2019_paper_9⟩ |
|
|
|
Context-Aware Zero-Shot Learning for Object RecognitionThirty-sixth International Conference on Machine Learning (ICML), Jun 2019, Long Beach, CA, United States |
|
|
Unsupervised Information Extraction: Regularizing Discriminative Approaches with Relation Distribution LossesACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Jul 2019, Florence, Italy. pp.1378-1387, ⟨10.18653/v1/P19-1133⟩ |
|
|
Incorporating Visual Semantics into Sentence Representations within a Grounded Space2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong Kong, China. pp.696-707, ⟨10.18653/v1/D19-1064⟩ |
|
|
Learning Multi-Modal Word Representation Grounded in Visual ContextAssociation for the Advancement of Artificial Intelligence (AAAI), Feb 2018, New Orleans, United States |
Représentations Gaussiennes pour le Filtrage Collaboratif15ème COnférence en Recherche d'Informations et Applications - CORIA 2018, May 2018, Rennes, France. ⟨10.24348/coria.2018.paper31⟩ |
|
|
|
Apprentissage multimodal de représentation de mots à l'aide de contexte visuelConférence sur l'Apprentissage Automatique, Jun 2018, Rouen, France |
|
|
Gaussian Embeddings for Collaborative Filtering40th International ACM SIGIR Conference on Research and Development in Information Retrieval, Aug 2017, Tokyo, Japan. pp.1065-1068, ⟨10.1145/3077136.3080722⟩ |
|
|
LIP6@CLEF2017: Multi-Modal Spatial Role Labeling using Word Embeddings Working notesCLEF 2017, 2017, Dublin, Ireland |
Apprentissage de Modèles de Langue Neuronaux pour la Recherche d'InformationConférence en Recherche d'Infomations et Applications, Mar 2016, Toulouse, France. pp.717-732 |
|
Multilabel classification on heterogeneous graphs with gaussian embeddingsEuropean Conference on Machine Learning and Principles and Practice of Knowledge Discovery, Sep 2016, Riva del garda, Italy |
|
Représentation temporelle des mots : application au clustering de micro-blogs.Conférence en Recherche d'Infomations et Applications, Mar 2016, Toulouse, France. pp.531-544 |
|
Graph Based Method Approach to the ImageCLEF2015 Task1 - Image AnnotationCLEF 2015 - Conference and Labs of the Evaluation forum, Sep 2015, Toulouse, France |
|
Leveraging Rating Behavior to Predict Negative Social TiesIEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Aug 2015, Paris, France. pp.623-628, ⟨10.1145/2808797.2809402⟩ |
|
Polarité des jugements et des interactions pour le filtrage collaboratif et la prédiction de liens sociauxCORIA 2015 - Conférence en Recherche d'Infomations et Applications - 12th French Information Retrieval Conference, Mar 2015, Paris, France. pp.139-154 |
|
Filtrage collaboratif et intégration de la polarité des notesConférence en Recherche d'Infomations et Applications - 11th French Information Retrieval Conference, Mar 2014, Nancy, France. pp.11-26 |
|
Quantum Mechanics and Information Retrieval: From Theory to Application4th International Conference on the Theory of Information Retrieval, ICTIR 2013, Oct 2013, Copenhagen, Denmark |
|
A comparison of static index pruning methods with temporal queriesSIGIR 2013 Workshop on Time-aware Information Access, TAIA2013, Jul 2013, Dublin, Ireland. pp.26-29 |
|
|
|
Méthodologie pour une représentation multi-dimensionnelle des documentsCORIA 2013 - 10ème COnférence en Recherche d'Information et Applications, Apr 2013, Neuchâtel, Suisse. pp.227-236 |
|
|
INEX 2007 Evaluation Measures6th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2007, Dagstuhl Castle, Germany, December 17-19, 2007, Revised and Selected Papers, Dec 2007, Dagstuhl, Germany |
|
|
INEX 2006 Evaluation MeasuresComparative Evaluation of XML Information Retrieval Systems: Fifth Workshop of the INitiative for the Evaluation of XML Retrieval (INEX 2006), Aug 2007, Dagstuhl, Germany |
An algebra for probabilistic XML RetrievalTDM 2004 - 1st Twente Data Management Workshop on XML Databases and Information Retrieval, Jun 2004, Enschede, Netherlands |
|
Filtering in XML Retrieval: a Prospective AnalysisSIGIR 2004 workshop on XML and Information Retrieval, Jul 2004, Sheffield, United Kingdom |
|
Interface pour l'évaluation de systèmes de recherche sur des documents XMLPremière Conférence en Recherche d'Information et Applications (CORIA'04), Mar 2004, Toulouse, France |
|
An Algebra for Structured Queries in Bayesian Networks3rd Workshop of the INitiative for the Evaluation of XML Retrieval (INEX'04), Dec 2004, Dagstuhl, Germany. pp.100-112, ⟨10.1007/11424550_9⟩ |
|
Structure, recherche d'information et apprentissageJournées francophones d'Extraction et de Gestion des Connaissances, Jan 2003, Lyon, France |
|
A Machine Learning Model for Information Retrieval with Structured DocumentsMLDM 2003 - 3rd International Conference on Machine Learning and Data Mining in Pattern Recognition, Jul 2003, Leipzig, Germany. pp.425-438, ⟨10.1007/3-540-45065-3_37⟩ |
|
Un modèle pour la recherche d’information sur des documents structurés6èmes Journées internationales d'Analyse statistique des Données Textuelles (JADT 2002), Mar 2002, Saint-Malo, France |
|
Bayesian networks and INEXFirst Annual Workshop of the Initiative for the Evaluation of XML retrieval (INEX), Dec 2002, Dagstuhl, Germany. pp.149-154 |
|
A Bayesian Network Model for Page Retrieval in a Hierarchically Structured CollectionXML Workshop of the 25th ACM SIGIR Conference, Aug 2002, Tampere, Finland |
|
Apprentissage et Recherche Documentaire : une Approche Probabiliste DifférentielleColloque Francophone sur l'Apprentissage Automatique (CAP'2000), 2000, Saint-Etienne, France |
|
Learning in Information Retrieval: a Probabilistic Differential ApproachBCS-IRSG, 22nd Annual Colloquium on Information Retrieval Research, Apr 2000, Sidney Sussex College, Cambridge, United Kingdom |
|
|
Probing Language Models on Their Knowledge SourceProceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP, Association for Computational Linguistic, pp.604-614, 2024, 979-8-89176-170-4. ⟨10.18653/v1/2024.blackboxnlp-1.35⟩ |
Introducción a la recuperación de informaciónRecuperación de Información. Un enfoque práctico y multidisciplinar, RA-MA, 2011 |
|
|
|
SpecificityLing Liu and M. Tamer Özsu. Encyclopedia of Database Systems, Springer-Verlag, 2007 |
|
|
Evaluation MetricsLing Liu and M. Tamer Özsu. Encyclopedia of Database Systems, Springer-Verlag, 2007 |
|
|
What Makes Multimodal In-Context Learning Work?2024 |
|
|
Training Table Question Answering via SQL Query Decomposition2024 |
|
|
A White Box Analysis of ColBERT2020 |
|
|
MLSUM: The Multilingual Summarization Corpus2020 |
|
|
ColdGANs: Taming Language GANs with Cautious Sampling Strategies2020 |
|
|
Discriminative Adversarial Search for Abstractive Summarization2020 |
|
|
Learning Term Weights for Ad-hoc Retrieval2016 |
Parameterized Neural Network Language Models for Information Retrieval2015 |
|
|
Efficient Document Indexing Using Pivot Tree[Research Report] Sorbonne Universités, UPMC Univ Paris 06, CNRS, LIP6 UMR 7606. 2016 |
Diversification Based Static Index Pruning - Application to Temporal Collections[Research Report] Sorbonne Universités, UPMC Univ Paris 06, CNRS, LIP6 UMR 7606. 2013 |
|
|
|
Beyond Cumulated Gain and Average Precision: Including Willingness and Expectation in the User Model[Research Report] Sorbonne Universités, UPMC Univ Paris 06, CNRS, LIP6 UMR 7606. 2012 |
The Kernel Quantum Probabilities (KQP) Library[Research Report] Sorbonne Universités, UPMC Univ Paris 06, CNRS, LIP6 UMR 7606. 2012 |
|
|
Learning Representation for Information AccessInformation Retrieval [cs.IR]. Sorbonne Université, 2020 |