Pascale Sébillot
84
Documents
Presentation
Publications since 2009
Publications depuis 2009
Publications
|
Text Recognition in Multimedia Documents: A Study of two Neural-based OCRs Using and Avoiding Character SegmentationInternational Journal on Document Analysis and Recognition, 2014, 17 (1), pp.19-31. ⟨10.1007/s10032-013-0202-7⟩
Journal articles
hal-00867225v1
|
|
Enhancing lexical cohesion measure with confidence measures, semantic relations and language model interpolation for multimedia spoken content topic segmentationComputer Speech and Language, 2012, 26 (2), pp.90-104
Journal articles
hal-00645705v1
|
|
Exploiting Speech for Automatic TV Delinearization: From Streams to Cross-Media Semantic NavigationEURASIP Journal on Image and Video Processing, 2011, 2011, 689780, 17 p. 2 columns. ⟨10.1155/2011/689780⟩
Journal articles
hal-00645216v1
|
|
Morpho-syntactic post-processing of N-best lists for improved French automatic speech recognitionComputer Speech and Language, 2010, 24 (4), pp.663-684. ⟨10.1016/j.csl.2009.10.001⟩
Journal articles
hal-00508471v1
|
|
Recherche de relation à partir d’un seul exemple fondée sur un modèle N-way K-shot : une histoire de distracteurs35èmes Journées d'Études sur la Parole (JEP 2024) 31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024) 26ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL 2024), Jul 2024, Toulouse, France. pp.157-168
Conference papers
hal-04623015v1
|
|
One-shot relation retrieval in news archives: adapting N-way K-shot relation classification for efficient knowledge extractionKES 2024 - 28th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, Sep 2024, Seville, Spain. pp.1060-1069
Conference papers
hal-04708239v1
|
|
Regularization, Semi-supervision, and Supervision for a Plausible Attention-Based Explanation28th International Conference on Natural Language and Information Systems (NLDB), Jun 2023, Derby, United Kingdom. pp.285-298
Conference papers
hal-04132646v1
|
|
Géométrie de l'auto-attention en classification : quand la géométrie remplace l'attentionCORIA-TALN 2023 - 18e 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, Jun 2023, Paris, France. pp.137-150
Conference papers
hal-04130184v2
|
|
Derrière les plongements de relationsCORIA-TALN 2023 - 18e 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, Jun 2023, Paris, France. pp.311-322
Conference papers
hal-04130142v2
|
|
Une étude statistique des plongements dans les modèles transformers pour le françaisTraitement Automatique des Langues Naturelles (TALN 2022), Jun 2022, Avignon, France. pp.247-256
Conference papers
hal-03701513v1
|
|
Confronting Active Learning for Relation Extraction to a Real-life Scenario on French Newspaper DataInterNLP 2022@NeurIPS - 2nd Workshop on Interactive Learning for Natural Language Processing, Dec 2022, New Orleans, United States. pp.1-7
Conference papers
hal-03839438v1
|
|
Filtrage et régularisation pour améliorer la plausibilité des poids d'attention dans la tâche d'inférence en langue naturelleTALN 2022 - Traitement Automatique des Langues Naturelles, Jun 2022, Avignon, France. pp.95-103
Conference papers
hal-03701492v1
|
|
Utilisation d'approches automatiques pour la reconnaissance des expériences de lectureHumanistica 2021 - Colloque de l'Association francophone des humanités numériques, May 2021, Rennes, France. pp.81-83
Conference papers
hal-03230027v1
|
|
" Je pense que ça traite d'expérience de lecture, à voir ... " : retour sur une expérience d'annotation collaborativeHumanistica 2021 - Colloque annuel de l'association francophone des humanités numériques, May 2021, Rennes, France. pp.84-85
Conference papers
hal-03230021v1
|
|
Active Learning for Interactive Relation Extraction in a French Newspaper's ArticlesRANLP 2021 - Recent Advances in Natural Language Processing, Sep 2021, Online, Bulgaria. pp.886-894
Conference papers
hal-03371917v1
|
|
A Study of the Plausibility of Attention between RNN Encoders in Natural Language InferenceICMLA 2021 - 20th IEEE International Conference on Machine Learning and Applications, Dec 2021, Pasadena, United States. pp.1-7
Conference papers
hal-03372669v1
|
|
IRISA System for Entity Detection and Linking at CLEF HIPE 2020Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum, Sep 2020, Thessaloniki, Greece
Conference papers
hal-02943717v2
|
|
A correlation-based entity embedding approach for robust entity linkingICTAI 2020 - IEEE 32nd International Conference on Tools with Artificial Intelligence, Nov 2020, Virtual, United States. pp.1-6
Conference papers
hal-02999303v1
|
|
A Novel Path-based Entity Relatedness Measure for Efficient Collective Entity LinkingInternational Semantic Web Conference (ISWC), Nov 2020, Athens, Greece
Conference papers
hal-02937580v1
|
|
Relation, es-tu là ? Détection de relations par LSTM pour améliorer l’extraction de relationsJEP-TALN-RECITAL 2020 - 6e conférence conjointe Journées d'Études sur la Parole (JEP, 33e édition), Traitement Automatique des Langues Naturelles (TALN, 27e édition), Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL, 22e édition). Volume 2 : Traitement Automatique des Langues Naturelles, Jun 2020, Nancy, France. pp.279-287
Conference papers
hal-02784777v3
|
|
Using Knowledge Base Semantics in Context-Aware Entity LinkingDocEng 2019 - 19th ACM Symposium on Document Engineering, Sep 2019, Berlin, Germany. pp.1-10, ⟨10.1007/978-3-030-27520-4_8⟩
Conference papers
hal-02171981v1
|
|
Disfluency Insertion for Spontaneous TTS: Formalization and Proof of ConceptSLSP 2018 - 6th International Conference on Statistical Language and Speech Processing, Oct 2018, Mons, Belgium. pp.1-12, ⟨10.1007/978-3-030-00810-9_4⟩
Conference papers
hal-01840798v1
|
|
Linking multimedia content for efficient news browsing2017 ACM International Conference on Multimedia Retrieval (ICMR), Jun 2017, Bucharest, Romania. ⟨10.1145/3078971.3079023⟩
Conference papers
hal-01522413v1
|
|
Ajout automatique de disfluences pour la synthèse de la parole spontanée : formalisation et preuve de conceptTraitement automatique du langage naturel (TALN), Jun 2017, Orléans, France
Conference papers
hal-01532031v2
|
|
Exploiting Multimodality in Video Hyperlinking to Improve Target DiversityMMM2017 - International Conference on Multimedia Modeling, Jan 2017, Reykyavik, Iceland. ⟨10.1007/978-3-319-51814-5_16⟩
Conference papers
hal-01498130v2
|
|
Language-based Construction of Explorable News Graphs for JournalistsEmpirical Methods in Natural Language Processing - Workshop on Natural Language Processing meets Journalism, 2017, Copenhague, Denmark. ⟨10.18653/v1/w17-4206⟩
Conference papers
hal-01578932v1
|
|
Statistical Pronunciation Adaptation for Spontaneous Speech SynthesisText, Speech and Dialogue (TSD), Aug 2017, Prague, Czech Republic
Conference papers
hal-01532035v1
|
|
Adaptation de la prononciation pour la synthèse de la parole spontanée en utilisant des informations linguistiquesJournées d'Études sur la Parole, Jul 2016, Paris, France
Conference papers
hal-01321361v1
|
|
IRISA at TRECVid2016: Crossmodality, Multimodality and Monomodality for Video HyperlinkingWorking Notes of the TRECVid 2016 Workshop, 2016, Gaithersburg, United States
Conference papers
hal-01400275v1
|
|
Shaping-Up Multimedia Analytics: Needs and Expectations of Media ProfessionalsThe 22nd International Conference on Multimedia Modelling, Special Session Perspectives on Multimedia Analytics, Jan 2016, Miami, United States
Conference papers
hal-01214829v1
|
|
Évaluation d'une nouvelle structuration thématique hiérarchique des textes dans un cadre de résumé automatique et de détection d'ancres au sein de vidéosConférence sur le Traitement Automatique des Langues Naturelles, 2016, Paris, France. pp.139-152
Conference papers
hal-01399670v1
|
|
Hierarchical topic structuring: from dense segmentation to topically focused fragments via burst analysisRecent Advances on Natural Language Processing, 2015, Hissar, Bulgaria
Conference papers
hal-01186443v1
|
Comparing corpora to identify learner-specific features of English: The case of this, that and itLearner Corpus Research Conference (LCR 2015), Radboud University, Sep 2015, Radboud, Netherlands. pp.68-69
Conference papers
hal-01239837v1
|
|
|
IRISA at MediaEval 2015: Search and Anchoring in Video Archives TaskWorking Notes Proceedings of the MediaEval Workshop, 2015, Wurzen, Germany
Conference papers
hal-01196176v1
|
|
Hierarchical Topic Models for Language-based Video HyperlinkingWorkshop on Speech, Language and Audio in Multimedia, 2015, Brisbane, Australia. ⟨10.1145/2802558.2814642⟩
Conference papers
hal-01186429v1
|
|
Probabilistic Speaker Pronunciation Adaptation for Spontaneous Speech Synthesis Using Linguistic FeaturesInternational Conference on Statistical Language and Speech Processing (SLSP), Nov 2015, Budapest, Hungary. pp.229-241
Conference papers
hal-01181192v1
|
|
Vers une typologie de liens entre contenus journalistiques22e conférence sur le Traitement Automatique des Langues Naturelles (TALN), Jun 2015, Caen, France. pp.515-521
Conference papers
hal-01196052v1
|
|
IRISA at TrecVid2015: Leveraging Multimodal LDA for Video HyperlinkingTRECVid 2015 Workshop, Nov 2015, Gaithersburg, United States
Conference papers
hal-01403726v1
|
|
IRISA and KUL at MediaEval 2014: Search and Hyperlinking TaskWorking Notes Proceedings of the MediaEval 2014 Workshop, Oct 2014, Barcelona, Spain
Conference papers
hal-01094850v1
|
|
Investigating domain-independent NLP techniques for precise target selection in video hyperlinkingISCA/IEEE Workshop on Speech, Language and Audio in Multimedia, Sep 2014, Penang, Malaysia
Conference papers
hal-01053698v1
|
Un modèle segmental probabiliste combinant cohésion lexicale et rupture lexicale pour la segmentation thématiqueTALN - Conférence sur le traitement automatique des langues naturelles, ATALA, Jun 2013, Les Sables d'Olonne, France
Conference papers
hal-00844112v1
|
|
|
Leveraging lexical cohesion and disruption for topic segmentationInternational Conference on Empirical Methods in Natural Language Processing, EMNLP 2013, Oct 2013, Seattle, United States. pp.1314--1324
Conference papers
hal-00867011v1
|
|
Multimedia Information Seeking through Search and HyperlinkingACM International Conference on Multimedia Retrieval, ICMR 2013, Apr 2013, Dallas, United States. 8 p., 2 columns
Conference papers
hal-00867090v1
|
|
HITS and IRISA at MediaEval 2013: Search and Hyperlinking TaskMediaEval working notes, 2013, Spain. pp.2
Conference papers
hal-00906249v1
|
|
Proper Noun Semantic Clustering using Bag-Of-VectorsANLP - Applied Natural Language Processing conference. Special track at the 25th International FLAIRS Conference., May 2012, Marco Island, FL, United States
Conference papers
hal-00760105v1
|
|
Combining Multi-Scale Character Recognition and Linguistic Knowledge for Natural Scene Text OCR10th IAPR International Workshop on Document Analysis Systems, DAS, Mar 2012, Gold Coast, Queensland, Australia. pp.120-124
Conference papers
hal-00753908v1
|
Automated processing of an English learner corpus: the case of this and thatICAME332012 : Corpora at the centre and crossroads of English linguistics, University of Leuven, May 2012, Louvain, Belgium
Conference papers
hal-01239864v1
|
|
|
IRISA at MediaEval 2012: Search and Hyperlinking TaskWorking Notes Proceedings of the MediaEval 2012, Oct 2012, Pisa, Italy. http://ceur-ws.org/Vol-927/
Conference papers
hal-00753909v1
|
|
Text Recognition in Videos using a Recurrent Connectionist Approach22th International Conference on Artificial Neural Networks, ICANN, Sep 2012, Lausanne, Switzerland. pp.172-179, ⟨10.1007/978-3-642-33266-1_22⟩
Conference papers
hal-00753906v1
|
|
Semantic Clustering using Bag-of-Bag-of-FeaturesCORIA - COnférence en Recherche d'Information et Applications, Mar 2012, Bordeaux, France. pp.229-244
Conference papers
hal-00753912v1
|
|
A Scalable Video Search Engine Based on Audio Content Indexing and Topic Segmentation2011 Networked and Electronic Media (NEM) Summit : Implementing Future Media Internet, Sep 2011, Torino, Italy. 160 p
Conference papers
hal-00645228v1
|
|
Reconnaissance automatique de texte dans des vidéos à l'aide d'un OCR et de connaissances linguistiquesGRETSI, Sep 2011, Bordeaux, France. 4 p., 2 columns
Conference papers
hal-00645217v1
|
|
A Comprehensive Neural-Based Approach for Text Recognition in Videos using Natural Language ProcessingACM International Conference on Multimedia Retrieval, ICMR, Apr 2011, Trento, Italy. 8 p., 2 columns
Conference papers
hal-00645219v1
|
Reconnaissance automatique de textes dans les vidéos à l’aide d’un OCR et de connaissances linguistiquesGroupe de Recherche et d'Etudes du Traitement du Signal (Gretsi 2011), Sep 2011, Bordeaux, France
Conference papers
hal-01354571v1
|
|
|
Automatically Finding Semantically Consistent N-grams to Add New Words in LVCSR SystemsIEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, May 2011, Prague, Czech Republic. 4 p., 2 columns
Conference papers
hal-00645223v1
|
Using shallow linguistic features for relation extraction in bio-medical textsTraitement Automatique des Langues Naturelles, TALN, 2011, Montpellier, France. 125-130, short paper
Conference papers
hal-00644070v1
|
|
|
L'adaptation thématique d'un modèle de langue fait-elle apparaître des mots thématiques?Journées d'Étude sur la Parole, May 2010, Mons, Belgium
Conference papers
inria-00555850v1
|
Improving ASR-based topic segmentation of TV programs with confidence measures and semantic relationsProc. Annual Intl. Speech Communication Association Conference (Interspeech), Sep 2010, Makuhari, Japan
Conference papers
inria-00555804v1
|
|
|
Utilisation de relations sémantiques pour améliorer la segmentation thématique de documents télévisuelsTraitement automatique des langues naturelles, TALN 2010, Jul 2010, Montréal, Canada
Conference papers
inria-00533389v1
|
|
Indices utiles à la cohésion lexicale pour la segmentation thématique de documents orauxXXVIIIe journées d'études de la parole, May 2010, Mons, Belgique
Conference papers
inria-00533388v1
|
|
Can automatic speech transcripts be used for large scale TV stream description and structuring?First International Workshop on Content-Based Audio/Video Analysis for Novel TV Services, CBTV'09, Dec 2009, San Diego, CA, United States. pp.489-494
Conference papers
hal-00762125v1
|
|
Constraint selection for topic-based MDI adaptation of language models10th Annual Conference of the International Speech Communication Association, Interspeech'09, Sep 2009, Brighton, United Kingdom. pp.368--371
Conference papers
hal-00760610v1
|
|
Un modèle multi-sources pour la segmentation en sujets de journaux radiophoniques15ème conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2008, Avignon, France. pp.49-58
Conference papers
hal-02021382v1
|
|
Morphosyntactic resources for automatic speech recognition6th International Conference on Language Resources and Evaluation (LREC), 2008, Marrakech, Morocco
Conference papers
hal-02021879v1
|
|
Morphosyntactic Processing of N-Best Lists for Improved Recognition and Confidence Measure Computation8th Annual Conference of the International Speech Communication Association (Interspeech), 2007, Antwerp, Belgium. pp.1741-1744
Conference papers
hal-02021878v1
|
|
Peut-on utiliser les étiqueteurs morphosyntaxiques pour améliorer la transcription automatique ?26èmes journées d'étude sur la parole (JEP), 2006, Dinard, France
Conference papers
hal-02021377v1
|
|
Are Morphosyntactic Taggers Suitable to Improve Automatic Transcription?9th International Conference on Text, Speech and Dialogue (TSD), 2006, Brno, Czech Republic. pp.391-398
Conference papers
hal-02021874v1
|
Varia - Préface - 59-1ATALA, 59 (1), pp.7-11, 2019
Books
hal-01789046v1
|
|
|
Actes de la conférence Traitement Automatique de la Langue Naturelle, TALN 20182018
Books
hal-01843560v1
|
|
Le traitement automatique des langues face aux données textuelles volumineuses et potentiellement dégradées : qu'est-ce que cela change ?Lisette Calderan; Pascale Laurent; Hélène Lowinger; Jacques Millet. Big data : nouvelles partitions de l'information. Actes du séminaire IST INRIA,, octobre 2014, De Boeck, pp.43-60, 2015, Information et stratégie, 978-2804189150
Book sections
hal-01056396v1
|
|
Automated classification of unexpected uses of this and that in a learner corpus of EnglishLieven Vandelanotte; Kristin Davidse; Caroline Gentens. Recent Advances in Corpus Linguistics: Developing and Exploiting Corpora, 78, Brill, pp.309-324, 2014, Rodopi Language and Linguistics Special E-Book, ⟨10.1163/9789401211130_015⟩
Book sections
hal-01058760v2
|
|
Automatic Acquisition of GL Resources, Using an Explanatory, Symbolic TechniqueAdvances in Generative Lexicon Theory, Springer, pp.ch19, 2013
Book sections
hal-00760258v1
|
|
Toward the Integration of Natural Language Processing and Automatic Speech Recognition: Using Morpho-Syntax and Pragmatics for TranscriptionPetros Maragos, Alexandros Potamianos, Patrick Gros. Multimodal Processing and Interaction: Audio, Video, Text, Springer US, pp.201-218, 2008, 978-0-387-76316-3. ⟨10.1007/978-0-387-76316-3_9⟩
Book sections
hal-02021921v1
|
|
Apprentissage sur corpus de relations lexicales sémantiques - La linguistique et l'apprentissage au service d'applications du traitement automatique des languesInterface homme-machine [cs.HC]. Université Rennes 1, 2002
Accreditation to supervise research
tel-00533657v1
|
Varia - Préface - 60-1Revue TAL : traitement automatique des langues, 60 (1), pp.7-11, 2020
Special issue
hal-02433763v1
|
|
Varia - Préface - 58-1Revue TAL : traitement automatique des langues, 58, pp.7-11, 2018
Special issue
hal-02181860v1
|
|
Varia - Préface - 57-1Revue TAL : traitement automatique des langues, 57 (1), pp.7-11, 2016
Special issue
hal-02433945v1
|