Sophie Rosset
Présentation
Publications
Publications
|
|
Format Matters: A Critical Evaluation of Output Formats for Prompting LLMs in SLU and NERThe Fifteenth biennial Language Resources and Evaluation Conference (LREC 2026), May 2026, Palma de Majorque, Spain |
|
|
Plongement des constituants pour la représentation sémantique des phrases20e 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), Jul 2025, Marseille, France. pp.614-628 |
|
|
Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot LearningInterspeech 2025, Aug 2025, Rotterdam, Netherlands. ⟨10.21437/Interspeech.2025-175⟩ |
|
|
Détection des contaminations de LLM par extraction de données : une revue de littérature pratique20e 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), Jul 2025, Marseille, France. pp.233-251 |
|
|
New Semantic Task for the French Spoken Language Understanding MEDIA BenchmarkThe 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, Torino, Italy. pp.12227-12246 |
|
|
Small Language Models are Good Too: An Empirical Study of Zero-Shot ClassificationThe 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, TURIN, Italy. pp.14923-14936 |
|
|
Nouvelle tâche sémantique pour le corpus de compréhension de parole en français MEDIA35èmes Journées d'Études sur la Parole (JEP 2024), Jul 2024, Toulouse, France. pp.470-480 |
|
|
Les petits modèles sont bons : une étude empirique de classification dans un contexte zero-shot31ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2024), Jul 2024, Toulouse, France. pp.113-129 |
|
|
mALBERT: Is a Compact Multilingual BERT Model Still Worth It?The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, Torino, Italy. pp.11023-11029 |
|
|
Tri-apprentissage génératif : génération de données pour de la reconnaissance d'entitées nommées semi-superviséCORIA-TALN 2023 30e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), Jun 2023, Paris, France. pp.68-79 |
|
|
Continual self-supervised domain adaptation for end-to-end speaker diarizationIEEE Spoken Language Technology Workshop (SLT 2022), IEEE Speech and Language Processing Technical Committee, Jan 2023, Doha, Qatar. pp.626 - 632, ⟨10.1109/SLT54892.2023.10023195⟩ |
|
|
Analyzing BERT Cross-lingual Transfer Capabilities in Continual Sequence LabelingFirst Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models, Oct 2022, virtual, South Korea |
|
|
Étude comparative de modèles Transformers en compréhension de la parole en français34e Journées d'Etudes sur la Parole (JEP2022), Jun 2022, Île de Noirmoutier, France. pp.721-730, ⟨10.21437/JEP.2022-76⟩ |
|
|
Attention Modulation for Zero-Shot Cross-Domain Dialogue State Tracking3rd Workshop on Computational Approaches to Discourse (CODI) at COLING 2022, Oct 2022, Gyeongju, South Korea. pp.86-91 |
|
|
On the Usability of Transformers-based models for a French Question-Answering taskJoint Conference of the Information Retrieval Communities in Europe (CIRCLE) 2022, Jul 2022, Samatan, France |
|
|
Benchmarking Transformers-based models on French Spoken Language Understanding tasksINTERSPEECH 2022, Sep 2022, Incheon, South Korea. pp.1238-1242, ⟨10.21437/Interspeech.2022-385⟩ |
|
|
Generating unlabelled data for a tri-training approach in a low resourced NER taskThird Workshop on Deep Learning for Low-Resource Natural Language Processing, Jul 2022, Hybrid, Seattle, United States. pp.30-37, ⟨10.18653/v1/2022.deeplo-1.4⟩ |
|
|
On the cross-lingual transferability of multilingual prototypical models across NLU tasksACL workshop on Meta Learning and Its Applications to Natural Language Processing (MetaNLP), 2021, Bangkok, Thailand. ⟨10.18653/v1/2021.metanlp-1.5⟩ |
|
|
On the Usability of Transformers-based models for a French Question-Answering taskRecent Advances in Natural Language Processing (RANLP), Sep 2021, Varna, Bulgaria. pp.244-255 |
|
|
Overlap-Aware Low-Latency Online Speaker Diarization Based on End-To-End Local SegmentationIEEE Automatic Speech Recognition and Unserstanding Workshop, Dec 2021, Cartagena, Colombia. pp.1139-1146, ⟨10.1109/ASRU51503.2021.9688044⟩ |
|
|
Où en sommes-nous dans la reconnaissance des entités nommées structurées à partir de la parole ?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 1 : Journées d'Études sur la Parole, 2020, Nancy, France. pp.64-72 |
Where are we in Named Entity Recognition from Speech?LREC 2020 - 12th Language Resources and Evaluation Conference, May 2020, Marseille, France. pp.4514‑4520 |
|
|
|
Evaluate on-the-job learning dialogue systems and a case study for natural language understandingWorkshop NeurIPS 2020 Human in the Loop Dialogue Systems, Dec 2020, Virtual only, United States |
|
|
What is best for Spoken Language Understanding: Small but Task-dependant Embeddings or Huge but Out-of-domain Embeddings?45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020), May 2020, Barcelona, Spain. pp.8114-8118, ⟨10.1109/ICASSP40776.2020.9053278⟩ |
|
|
A Metric Learning Approach to Misogyny CategorizationWorkshop on Representation Learning for NLP, Jul 2020, Online, France. pp.89-94, ⟨10.18653/v1/2020.repl4nlp-1.12⟩ |
|
|
A Cooking Knowledge Graph and Benchmark for Question Answering Evaluation in Lifelong Learning ScenariosInternational Conference on Applications of Natural Language to Information Systems, Elisabeth Métais and Farid Meziane and Helmut Horacek and Philipp Cimiano, Jun 2020, Saarbrücken, Germany |
|
|
Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation TaskIn Proceedings of The 28th International Conference on Computational Linguistics (COLING’2020), 2020, Dec 2020, Barcelona (online), Spain. pp.2722-2727, ⟨10.18653/v1/2020.coling-main.245⟩ |
|
|
A Comparison of Metric Learning Loss Functions for End-To-End Speaker VerificationInternational Conference on Statistical Language and Speech Processing, Oct 2020, Cardiff, United Kingdom. pp.137-148, ⟨10.1007/978-3-030-59430-5_11⟩ |
|
|
Lifelong learning and task-oriented dialogue system: what does it mean?International Workshop on Spoken Dialogue Systems Technology, Apr 2019, Siracusa, Italy |
|
|
Do You Need Embeddings Trained on a Massive Specialized Corpus for Your Clinical Natural Language Processing Task?17th World Congress on Medical and Health Informatics (MEDINFO), MCO Congress Group, Aug 2019, Lyon, France. pp.1558-1559, ⟨10.3233/SHTI190533⟩ |
LIHLITH: Learning to Interact with Humans by Lifelong Interaction with HumansSpanish Conference for Natural Language Processing (Sociedad Española para el Procesamiento del Lenguaje Natural), Sep 2019, Bilbao, Spain |
|
Terminological and language resources for developing a virtual patient dialogue system in SpanishSpanish Conference for Natural Language Processing (Sociedad Española para el Procesamiento del Lenguaje Natural), Sep 2019, Bilbao, Spain |
|
|
|
Detecting context-dependent sentences in parallel corpora25th Conférence sur le Traitement Automatique des Langues Naturelles, 2018, Rennes, France. pp.393-400 |
|
|
Natural language understanding for task oriented dialog in the biomedical domain in a low ressources contextMachine Learning for Health - Workshop at NeurIPS 2018, Dec 2018, Montréal, Québec, Canada |
|
|
Étiquetage en parties du discours de langues peu dotées par spécialisation des plongements lexicauxConférence sur le Traitement Automatique des Langues Naturelles, May 2018, Rennes, France |
|
|
Resources and Methods for the Automatic Recognition of Place Names in AlsatianCorpus-Based Research in the Humanities, Jan 2018, Vienna, Austria. pp.35-44 |
How to Personalize Conversational Coaches for Stress Management?International Workshop on Computing For Well-Being, Oct 2018, Singapore, Singapore. pp.718-721, ⟨10.1145/3267305.3267698⟩ |
|
|
|
Corpora with Part-of-Speech Annotations for Three Regional Languages of France: Alsatian, Occitan and Picard11th edition of the Language Resources and Evaluation Conference, May 2018, Miyazaki, Japan |
|
|
Multifaceted Engagement in Social Interaction with a Machine: The JOKER Project2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), May 2018, Xi'an, China. pp.697-701, ⟨10.1109/FG.2018.00110⟩ |
|
|
Graph-Based Relation Validation MethodKnowledge Engineering and Knowledge Management, Nov 2016, Bologne, Italy |
|
|
Expériences d'étiquetage morphosyntaxique dans le cadre du projet RESTAUREAtelier DiLiTAL, Jun 2017, Orléans, France |
|
|
Community graph and linguistic analysis to validate relationships for knowledge base population4th International Symposium on Information Management and Big Data (SimBig 2017), Sep 2017, Lima, Peru |
|
|
NELIDA : assistant opérationnel générique apprenant incrémentalement par l'interactionConférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle, Jul 2017, Caen, France |
|
|
Automatic classification of doctor-patient questions for a virtual patient record query taskBioNLP Shared-Task Workshop, ACL, Jan 2017, Vancouver, Canada. pp.333-341, ⟨10.18653/v1/W17-2343⟩ |
|
|
Graphe de communauté pour la validation de relations dans le cadre de la population de bases de connaissancesCORIA, Mar 2017, Marseiile, France. ⟨10.24348/coria.2017.37⟩ |
|
|
Combining word and entity embeddings for entity linking14th Extended Semantic Web Conference - ESCW 2017, May 2017, Portorož, Slovenia. pp.337-352, ⟨10.1007/978-3-319-58068-5_21⟩ |
|
|
Utterance Retrieval based on Recurrent Surface Text Patterns39th European Conference on Information Retrieval, Apr 2017, Aberdeen, United Kingdom |
|
|
Apprendre des représentations jointes de mots et d'entités pour la désambiguïsation d'entités24ème Conférence sur le Traitement Automatique des Langues Naturelles - TALN 2017, LLL (Laboratoire Ligérien de Linguistique); LIFO (Laboratoire d’Informatique Fondamentale d’Orléans); LI (Laboratoire Informatique) de Tours, Jan 2017, Orléans, France. pp.182-195 |
Estimation de la qualité d'un système de reconnaissance de la parole pour une tâche de compréhension31ème Journées d’Études sur la Parole, 2016, Paris, France |
|
|
|
Comparing System-response Retrieval Models for Open-domain and Casual Conversational AgentSecond Workshop on Chatbots and Conversational Agent Technologies (WOCHAT@IVA2016), 2016, Los Angeles, United States |
|
|
The CAMOMILE Collaborative Annotation Platform for Multi-modal, Multi-lingual and Multi-media DocumentsLREC 2016 Conference, May 2016, Portoroz, Slovenia. pp.1421-1425 |
|
|
TAC KBP 2016 Cold Start Slot Filling and Slot Filler Validation Systems by IRT SystemXText Analysis Conference, National Institute of Standards and Technology, Nov 2016, Gaithersburg, Maryland, United States |
|
|
Joker ChatterbotWorkshop on Collecting and Generating Resources for Chatbots and Conversational Agents - Development and Evaluation, May 2016, Portorož, Slovenia |
|
|
Named Entity Resources - Overview and OutlookLanguage Resources and Evaluation, 2016, Portorož, Slovenia |
|
|
Purely Corpus-based Automatic Conversation Authoring10th edition of the Language Resources and Evaluation Conference (LREC), May 2016, Portorož, Slovenia. pp.ISBN: 978-2-9517408-9-1 |
Identification de facteurs de risque pour des patients diabétiques à partir de comptes-rendus cliniques par des approches hybridesConférence sur le Traitement Automatique des Langues Naturelles, Jan 2015, Caen, France. pp.25-36 |
|
|
|
Nao is doing humour in the CHIST-ERA JOKER project16th Interspeech, Sep 2015, Dresde, Germany. pp.1072-1073 |
How to Evaluate ASR Output for Named Entity Recognition?16th Annual Conference of the International Speech Communication Association (Interspeech'15), Sep 2015, Dresden, Germany. pp.1289-1293, ⟨10.21437/Interspeech.2015-322⟩ |
|
Morpho-Syntactic Study of Errors from Speech Recognition SystemInternational Conference on Language Resources and Evaluation, Jan 2014, Reykjavik, Iceland |
|
|
|
Person Instance Graphs for Named Speaker Identification in TV BroadcastOdyssey 2014: The Speaker and Language Recognition Workshop, Jun 2014, Joensuu, Finland. pp.179-186, ⟨10.21437/Odyssey.2014-28⟩ |
Risk factor identification from clinical records for diabetic patients.7th i2b2 Shared-Task and Workshop on Challenges in Natural Language Processing for Clinical Data, AMIA 2014 Affiliate Meeting: i2b2/UTHealth, Nov 2014, Washington DC, United States |
|
A CRF-Based Approach to Automatic Disfluency Detection in a French Call-Centre Corpus15th Annual Conference of the International Speech Communication Association (Interspeech'14), International Speech Communication Association (ISCA), Sep 2014, Singapour, Singapore. pp.2897-2901, ⟨10.21437/Interspeech.2014-601⟩ |
|
Comment évaluer la qualité des transcriptions automatiques pour la détection d’entités nommées ?XXXe Journées d'Études sur la Parole (JEP'14), Jun 2014, Le Mans, France. pp.430-437 |
|
Disfluences dans la parole spontanée conversationnelle: détection automatique utilisant des indices lexicaux et acoustiquesActes de la conférence conjointe JEP-TALN-RECITAL 2012, volume 2: TALN, pages 359–366, Jun 2014, Grenoble, France |
|
ETER: a New Metric for the Evaluation of Hierarchical Named Entity RecognitionLREC 2014 - 9th International Conference on Language Resources and Evaluation, European Language Resources Association (ELRA), May 2014, Reykjavik, Iceland. pp.3987-3994 |
|
Automatic named entity pre-annotation for out-of-domain human annotationLinguistic Annotation Workshop, ACL, Jan 2013, Sofia, Bulgaria. pp.168-177 |
|
Human annotation of asr error regions: Is ”gravity” a sharable concept for human annotators?Errors by Humans and Machines in Multimedia, Multimodal, Multilingual Data Processing (ERRARE 2013), Nov 2013, Ermenonville, France |
|
|
|
QCompere @ REPERE 2013SLAM 2013 - First Workshop on Speech, Language and Audio for Multimedia, Aug 2013, Marseille, France. pp.49-54 |
|
|
Unsupervised naming of speakers in broadcast TV: using written names, pronounced names or both ?the 14rd Annual Conference of the International Speech Communication Association, INTERSPEECH, Aug 2013, Lyon, France. pp.1462-1466, ⟨10.21437/Interspeech.2013-380⟩ |
Quel est l’apport de la détection d’entités nommées pour l’extraction d’information en domaine restreint?Conférence sur le Traitement Automatique des Langues Naturelles (TALN 2012), Jun 2012, Grenoble, France. pp.359-366 |
|
|
|
Structured Named Entities in two distinct press corpora: Contemporary Broadcast News and Old Newspapers6th Linguistics Annotation Workshop (The LAW VI), Jul 2012, Jeju, South Korea. pp.40-48 |
|
|
Methods combination and ML-based re-ranking of multiple hypothesis for question-answering systemsProceedings of the Workshop on Innovative Hybrid Approaches to the Processing of Textual Data, EACL, Apr 2012, Avignon, France. pp.87--96 |
|
|
Modeling the Complexity of Manual Annotation Tasks: a Grid of AnalysisInternational Conference on Computational Linguistics, Dec 2012, Mumbaï, India. pp.895--910 |
Modelling pause duration as a function of contextual lengthAnnual Conference of the International Speech Communication Association (INTERSPEECH 2012), 2012, Portland, United States. pp.659-662, ⟨10.21437/Interspeech.2012-203⟩ |
|
|
|
Manual Corpus Annotation: Giving Meaning to the Evaluation MetricsInternational COLING 2012: 24th Conference on Computational Linguistics, Dec 2012, Mumbaï, India. pp.809-818 |
|
|
Fusion of Speech, Faces and Text for Person Identification in TV BroadcastECCV 2012 - 12th European Conference on Computer Vision, Oct 2012, Firenze, Italy. pp.385-394, ⟨10.1007/978-3-642-33885-4_39⟩ |
|
|
Résolution des coréférences dans des comptes rendus cliniques. Une expérimentation issue du défi i2b2/VA 2011RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3 |
|
|
Tree-Structured Named Entity Recognition on OCR Data: Analysis, Processing and ResultsLREC 2012 - 8th International Conference on Language Resources and Evaluation, May 2012, Istanbul, Turkey |
Extended named entities annotation on OCRed documents: from corpus constitution to evaluation campaignLREC 2012 - 8th International Conference on Language Resources and Evaluation, May 2012, Istanbul, Turkey. pp.3126-3131 |
|
|
|
Fusion des réponses de systèmes de question-réponses.CORIA, Mar 2012, Bordeaux, France. pp.99--110, ⟨10.24348/coria.2012.99⟩ |
|
|
Tree Representations in Probabilistic Models for Extended Named Entities DetectionEuropean Chapter of the Association for Computational Linguistics, Apr 2012, Avignon, France |
Designing french tale corpora for entertaining text to speech synthesisLREC 2012 - 8th International Conference on Language Resources and Evaluation, May 2012, Istanbul, Turkey. pp.1003-1010 |
|
|
|
Proposal for an Extension of Traditional Named Entitites: from Guidelines to Evaluation, an Overview5th Linguistics Annotation Workshop (The LAW V), Jun 2011, Portland, United States. pp.92--100 |
Prosodic Analysis of a Corpus of Tales12th Annual Conference of the International Speech Communication Association (Interspeech'11), International Speech Communication Association (ISCA), Aug 2011, Florence, Italy. pp.3129-3132, ⟨10.21437/Interspeech.2011-783⟩ |
|
|
|
Extraction de patrons sémantiques appliquée à la classification d'Entités NomméesTALN'2011, 2011, Montpellier, France |
|
|
Named and specific entity detection in varied data: the Quaero named entity baseline evaluation7. Conference on international language resources and evaluation, May 2010, Valletta, Malta |
Hybrid Citation Extraction from PatentsLREC 2010 - 7th International Conference on Language Resources and Evaluation, 2010, La Valette, Malta |
|
|
|
Question answering on web data : the QA evaluation in QuaeroInternational Conference on Language Resources and Evaluation, Jan 2010, Valetta, Malta |
CARAMBA: Concept, Assertion, and Relation Annotation using Machine-learning Based Approachesi2b2 Medication Extraction Challenge Workshop, Nov 2010, Washington, United States |
|
|
|
Collecte et analyses de réponses naturelles pour les systèmes de questions-réponsesTALN 2009, Jun 2009, Senlis, France. pp.10 |
|
|
Semantic Relations for an Oral and Interactive Question-Answering System.SRSL7 (Semantic Representation of Spoken Language 2007), Nov 2007, Salamanca, Spain. pp.12-19 |
|
|
Results of the French Evalda-Media evaluation campaign for literal understandingThe fifth international conference on Language Resources and Evaluation (LREC 2006), May 2006, Genes, Italy |
Multi-level Information and Automatic dialog Acts Detection in human-human Spoken DialogsInterspeech, Sep 2005, Lisbon, Portugal. pp.2789-2792, ⟨10.21437/Interspeech.2005-822⟩ |
|
Détection automatique d’actes de dialogueTALN, Jun 2005, Dourdan, France. pp.283-292 |
|
|
|
Constitution d'un corpus de dialogue oral pour l'évaluation automatique de la compréhension hors- et en- contexte du dialogueJournées d'Etudes sur la Parole (JEP 2004), 2004, Fès, Maroc. pp.357-360 |
|
|
Predictive and objective evaluation of speech understanding: the challenge evaluation campaign of the I3 speech workgroup of the French CNRS3rd International Conference on Language Resources and Evaluation (LREC 2002), May 2002, Las Palmas, Spain |
|
|
AtomicEval: Evaluation Framework for Atomic Proposition Autonomy with French Propositioner10th Junior Conference on Data Sciences and Engineering, Sep 2025, Gif-sur-Yvette, France. |
A Natural Language Processing-based Microservice System for Healthcare ScenariosIEE International Conference on Biomedical and Health Informatics, Jul 2021, Virtual, France |
|
|
|
On the cross-lingual transferability of multilingual prototypical models across NLU tasksACL-IJCNLP 2021, Aug 2021, Bangkok, Thailand |
Un patient virtuel dialogant pour la formation des étudiants en médecineSymposium satellite francophone sur le traitement automatique des langues dans le domaine biomédical, Aug 2019, Lyon, France |
|
Human Annotation of ASR Error Regions: is "gravity" a Sharable Concept for Human Annotators?LREC 2014 - 9th International Conference on Language Resources and Evaluation, May 2014, Reykjavik, Iceland. , pp.3050-3056, 2014 |
|
Disfluences dans la parole spontanée conversationnelle : détection automatique utilisant des indices lexicaux et acoustiquesXXXe Journées d'Étude sur la Parole (JEP'14), Jun 2014, Le Mans, France. , Actes des XXXe Journées d'Étude sur la Parole (JEP'14), pp.366-373, 2014 |
Varia - Préface - 59-1ATALA, 59 (1), pp.7-11, 2019 |
|
Named Entities for Computational Linguistics2016 |
|
Les entités nommées pour le traitement automatique des languesISTE, 2015, 9781784051044 |
|
Traitements automatiques de l’oral et de l’écrit141, pp.4-8, 2014 |
|
|
Impact of Entity Graphs on Extracting Semantic RelationsSpringer. Information Management and Big Data.4th Annual International Symposium, SIMBig 2017, Lima, Peru, September 4-6, 2017, Revised Selected Papers, 795, pp.31-47, 2018, Communications in Computer and Information Science, ⟨10.1007/978-3-319-90596-9_3⟩ |
Media : évaluation de la compréhension dans les systèmes de dialogueStéphane Chaudiron; Khalid Choukri. L'évaluation des technologies de traitement de la langue, les campagnes Technolangue, Hermès, Lavoisier, pp.209-232, 2008, Cognition et traitement de l'information, 978-2746219922 |
Towards a storytelling humanoid robot2010, 4p |
|
|
LIMSI_UPV at SemEval-2020 Task 9: Recurrent Convolutional Neural Network for Code-mixed Sentiment Analysis2021 |