Benoit Favre
141
Documents
Presentation
**Full Professor** of Computer Science (CNU 27) at [Polytech](https://polytech.univ-amu.fr/), [Aix-Marseille Université](https://www.univ-amu.fr/)
- Member of [TALEP](https://talep.lis-lab.fr/) natural language processing research group at [Laboratoire d'Informatique et Systèmes](https://www.lis-lab.fr/) (LIS), CNRS UMR 7020
- benoit.favre at lis-lab.fr, <https://pageperso.lis-lab.fr/benoit.favre/>
**Responsabilities**
- Head of Data science branch of LIS
- Responsible for industry relations, CS dept of Polytech Marseille
- Member of scientific council of [Mésocentre](https://mesocentre.univ-amu.fr/) supercomputer at AMU
- Member of scientific committee of “AI for Health” [Laënnec](https://www.univ-amu.fr/fr/public/institut-laennec) Institute
- Member of scientific committee of “data for research” [CEDRE](https://cedre.univ-amu.fr/) project
- Head of the "multimodality and intermodality" axis of the CNRS [research group on NLP](https://gdr-tal.ls2n.fr/) (GdR TAL)
- President of the permanent organizing committee of the [TALN conference](https://www.atala.org/-Conference-TALN-RECITAL) (CPERM)
- Member of the editorial board of the [journal TAL](https://www.atala.org/revuetal)
- Chairman of ETAL NLP summer school
**Education / positions**
- HDR thesis, "Contextual natural language processing", Aix-Marseille University, 2019
- PhD thesis, "Automatic speech summarization", Avignon University, 2007
- Education: BSc & MSc Computer science and engineering, Avignon University, 1998-2004
- Post-doc UC Berkeley, USA 2007-2009
- Post-doc Le Mans University, France 2009-2010
- Associate professor Aix-Marseille University, France, 2010-2021
- Full professor Aix-Marseille University, France, 2021-
- Visiting Researcher at QUT Brisbane, Australia 2018
- Visiting Teacher at NIT Mizoram, India 2017
Publications
|
Unified Framework for Spoken Language Understanding and Summarization in Task-Based Human Dialog processingINTERSPEECH 2024, Sep 2024, Kos Island, Greece
Conference papers
hal-04615307v1
|
Tâches et systèmes de sélection automatique de réponses à des QCM dans le domaine médical : Présentation de la campagne DEFT 202435èmes 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.1-10
Conference papers
hal-04635890v1
|
|
|
ChiCA: un corpus de conversations face-à-face vs. Zoom entre enfants et parents35èmes 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.4-5
Conference papers
hal-04622994v1
|
|
Approche multitâche pour l'amélioration de la fiabilité des systèmes de résumé automatique de conversation35èmes 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.338-351
Conference papers
hal-04623026v1
|
|
From speech to primate vocalizations: self-supervised deep learning as a comparative approachProceedings of the 15th International Conference on the Evolution of Language (EVOLANG XV), Gary Lupyan, May 2024, Madison, United States. pp.64, ⟨10.17617/2.3587960⟩
Conference papers
hal-04608044v1
|
|
OLISIA: a Cascade System for Spoken Dialogue State TrackingEleventh Dialog System Technology Challenge, Sep 2023, Prague, Czech Republic. pp.95-104
Conference papers
hal-04072601v2
|
|
Towards an Exhaustive Evaluation of Vision-Language Foundation ModelsICCV workshop on Multimodal Foundation Models (MMFM), Oct 2023, Paris, France
Conference papers
hal-04181190v1
|
|
LIS@DEFT'23 : les LLMs peuvent-ils répondre à des QCM ? (a) oui; (b) non; (c) je ne sais pas.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, 2023, Paris, France. pp.46-56
Conference papers
hal-04131578v1
|
|
ASR-Generated Text for Language Model Pre-training Applied to Speech TasksInterspeech 2022, Sep 2022, Incheon, South Korea
Conference papers
hal-03770506v1
|
|
Using ASR-Generated Text for Spoken Language ModelingProceedings of BigScience Episode #5 -- Workshop on Challenges & Perspectives in Creating Large Language Models, May 2022, virtual+Dublin, France. pp.17-25, ⟨10.18653/v1/2022.bigscience-1.2⟩
Conference papers
hal-03770460v1
|
|
Simulation d’erreurs d’OCR dans les systèmes de TAL pour le traitement de données anachroniquesTraitement Automatique des Langues Naturelles, 2022, Avignon, France. pp.78-87
Conference papers
hal-03701471v1
|
|
Are Vision-Language Transformers Learning Multimodal Representations? A Probing PerspectiveAAAI 2022, Feb 2022, Vancouver, Canada
Conference papers
hal-03521715v2
|
|
Do Vision-and-Language Transformers Learn Grounded Predicate-Noun Dependencies?Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing., 2022, Abu Dhabi, United Arab Emirates
Conference papers
hal-03823490v1
|
|
Transferring Modern Named Entity Recognition to the Historical Domain: How to Take the Step?Workshop on Natural Language Processing for Digital Humanities (NLP4DH), Dec 2021, Silchar (Online), India
Conference papers
hal-03550384v1
|
|
Filtering conversations by dialogue act labels for improving corpus-based convergence studies21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, 2020, Virtual (Boise), United States
Conference papers
hal-03224185v1
|
Development of Multi-level Linguistic Alignment in Child-Adult ConversationsProceedings of the 11th Workshop on Cognitive Modeling and Computational Linguistics, 2020, online, France
Conference papers
hal-03580925v1
|
|
|
Analyse sémantique robuste par apprentissage antagoniste pour la généralisation de domaine6e 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 4 : Démonstrations et résumés d'articles internationaux, 2020, Nancy, France. pp.71-72
Conference papers
hal-02768521v3
|
|
Designing an IIR Research Apparatus with Users with Severe Intellectual DisabilityACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR), Mar 2020, Vancouver, Canada. pp.412-416, ⟨10.1145/3343413.3378008⟩
Conference papers
hal-02470797v1
|
|
A Framework for Information Accessibility in Large Video RepositoriesACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR), Mar 2020, Vancouver, Canada. ⟨10.1145/3343413.3378003⟩
Conference papers
hal-02470812v1
|
|
Engaging the Abilities of Participants with Intellectual Disability in IIR ResearchACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR), Mar 2020, Vancouver, Canada
Conference papers
hal-02470823v1
|
|
Neural Representations of Dialogical History for Improving Upcoming Turn Acoustic Parameters PredictionInterspeech 2020, Oct 2020, Virtual (Shangai), China. pp.4203-4207, ⟨10.21437/interspeech.2020-2785⟩
Conference papers
hal-03224194v1
|
|
Visual Disambiguation of Preprositional Phrase Attachments : Multimodal Machine Learning for Syntactic Analysis CorrectionIWANN: International Work-Conference on Artificial Neural Networks, Jun 2019, Gran Canaria, Spain. ⟨10.1007/978-3-030-20521-8_52⟩
Conference papers
hal-02465051v1
|
|
Typological Features for Multilingual Delexicalised Dependency Parsing2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Jun 2019, Minneapolis, United States. pp.3919-3930, ⟨10.18653/v1/N19-1393⟩
Conference papers
hal-02278897v1
|
|
Robust Semantic Parsing with Adversarial Learning for Domain GeneralizationProceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, Jun 2019, Minneapolis - Minnesota, France. pp.166-173, ⟨10.18653/v1/N19-2021⟩
Conference papers
hal-02298402v1
|
|
CAN WE PREDICT SELF-REPORTED CUSTOMER SATISFACTION FROM INTERACTIONS?2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2019, Brighton, United Kingdom. ⟨10.1109/ICASSP.2019.8683896⟩
Conference papers
hal-02439687v1
|
|
Correction automatique d'attachements prépositionnels par utilisation de traits visuels25ème conférence sur le Traitement Automatique des Langues Naturelles, May 2018, Rennes, France
Conference papers
hal-01832979v1
|
|
Replicating Speech Rate Convergence Experiments on the Switchboard CorpusWorkshop on Replicability and Reproducibility of Research Results in Science and Technology of Language, May 2018, Miyazaki, Japan
Conference papers
hal-01807796v1
|
|
Évaluation automatique de la satisfaction client à partir de conversations de type "chat" par réseaux de neurones récurrents avec mécanisme d’attention25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2018, Rennes, France
Conference papers
hal-01943265v1
|
|
Adding Syntactic Annotations to Flickr30k Entities Corpus for Multimodal Ambiguous Prepositional-Phrase Attachment Resolution11th edition of the Language Resources and Evaluation Conference, May 2018, Miyazaki, Japan
Conference papers
hal-01832930v1
|
|
Fusion multimodale image/texte par réseaux de neurones profonds pour la classification de documents imprimés15e Conférence en Recherche d’Information et Applications (CORIA), May 2018, Rennes, France
Conference papers
hal-01905242v1
|
|
Détection d'erreurs dans des transcriptions OCR de documents historiques par réseaux de neurones récurrents multi-niveau25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), May 2018, Rennes, France
Conference papers
hal-01905258v1
|
|
Apprentissage d'agents conversationnels pour la gestion de relations clients24e Conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2017, Orleans, France
Conference papers
hal-01773218v1
|
|
Correcting prepositional phrase attachments using multimodal corporaThe 15th International Conference on Parsing Technologies, Sep 2017, Pise, Italy
Conference papers
hal-01693292v1
|
|
Evaluation of word embeddings against cognitive processes: primed reaction times in lexical decision and naming tasksProceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP, 2017, Copenhagen, Denmark. pp.21 - 26
Conference papers
hal-01773220v1
|
|
Détection de coréférences de bout en bout en françaisTALN 2017, Jun 2017, Orléans, France
Conference papers
hal-01687116v1
|
Word embedding evaluation and combination10th edition of the Language Resources and Evaluation Conference (LREC 2016), 2016, Portorož, Slovenia
Conference papers
hal-01433185v1
|
|
|
Beyond utterance extraction: summary recombination for speech summarizationInterspeech, San Francisco (USA), 2016, San Francisco, United States
Conference papers
hal-01454927v1
|
|
Fusion d'espaces de représentations multimodaux pour la reconnaissance du rôle du locuteur dans des documents télévisuelsActes de la conférence JEP 2016, Jul 2016, Paris, France
Conference papers
hal-01454928v1
|
|
A Document Repository for Social Media and Speech ConversationsLanguage Resources and Evaluation Conference (LREC), 2016, Unknown, Unknown Region
Conference papers
hal-01454924v1
|
|
Joint syntactic and semantic analysis with a multitask Deep Learning Framework for Spoken Language UnderstandingInterspeech, ISCA, 2016, San Francisco, United States
Conference papers
hal-01454929v1
|
|
Détection de concepts pertinents pour le résumé automatique de conversations par recombinaison de patronsActes de la conférence TALN 2016, 2016, Paris, France
Conference papers
hal-01454926v1
|
TALEP @ DEFT'15 : Le plus cooool des systèmes d'analyse de sentimentActes de la 11e Défi Fouille de Texte, 2015, Caen, France. pp.97--103
Conference papers
hal-01194235v1
|
|
Speaker diarization through speaker embeddingsEUSIPCO, 2015, Unknown, Unknown Region
Conference papers
hal-01194233v1
|
|
Identification de personnes dans des flux multimédiaCORIA 2015 - Conférence en Recherche d'Infomations et Applications - 12th French Information Retrieval Conference, Mar 2015, PARIS, France. pp.239-251
Conference papers
hal-01194234v1
|
|
Adapting lexical representation and OOV handling from written to spoken language with word embeddingInterspeech, 2015, Dresden, Germany
Conference papers
hal-01194228v1
|
|
Rapid FrameNet annotation of spoken conversation transcriptsJoint ACL-ISO Workshop on Interoperable Semantic Annotation, 2015, Unknown, Unknown Region
Conference papers
hal-01194232v1
|
|
|
Concept-based Summarization using Integer Linear Programming: From Concept Pruning to Multiple Optimal SolutionsConference on Empirical Methods in Natural Language Processing (EMNLP) 2015, Sep 2015, Lisbonne, Portugal
Conference papers
hal-01203750v1
|
|
Multimodal embedding fusion for robust speaker role recognition in video broadcastAutomatic Speech Recognition and Understanding, Dec 2015, Scottsdale, United States. pp.383 - 389, ⟨10.1109/ASRU.2015.7404820⟩
Conference papers
hal-01475413v1
|
``Speech is silver, but silence is golden'': improving speech-to-speech translation performance by slashing users inputInterspeech, 2015, Unknown, Unknown Region
Conference papers
hal-01194229v1
|
|
Call Centre Conversation Summarization: A Pilot Task at Multiling 2015Sigdial, 2015, Unknown, Unknown Region
Conference papers
hal-01194231v1
|
|
MultiLing 2015: Multilingual Summarization of Single and Multi-Documents, On-line Fora, and Call-center ConversationsSigdial, 2015, Unknown, Unknown Region
Conference papers
hal-01194230v1
|
|
Automatically enriching spoken corpora with syntactic information for linguistic studiesLREC, 2014, Unknown, Unknown Region
Conference papers
hal-01194241v1
|
|
Speaker adaptation of DNN-based ASR with i-vectors: Does it actually adapt models to speakers?Interspeech, Singapore, 2014, Unknown, Unknown Region
Conference papers
hal-01194245v1
|
|
A Repository of State of the Art and Competitive Baseline Summaries for Generic News SummarizationLREC, 2014, Unknown, Unknown Region
Conference papers
hal-01194243v1
|
|
Joint Decoding of Complementary UtterancesSpoken Languge Technologies (SLT), Lake Tahoe (USA), 2014, Unknown, Unknown Region
Conference papers
hal-01194247v1
|
|
Correction interactive de transcriptions de parole par fusion de phrasesActes de la conférence JEP 2014, 2014, Le Mans, France
Conference papers
hal-01194238v1
|
|
Reranked aligners for interactive transcript correctionICASSP2014 - Speech and Language Processing (ICASSP2014 - SLTC), 2014, Florence, Italy
Conference papers
hal-01194237v1
|
|
Scene understanding for identifying persons in TV shows: beyond face authentication12th International Workshop on Content-Based Multimedia Indexing (CBMI), Klagenfurt (Austria), 2014, Unknown, Unknown Region
Conference papers
hal-01194242v1
|
|
Retrieving the syntactic structure of erroneous ASR transcriptions for open-domain Spoken Language UnderstandingICASSP2014 - Speech and Language Processing (ICASSP2014 - SLTC), 2014, Florence, Italy
Conference papers
hal-01194236v1
|
|
Adapting dependency parsing to spontaneous speech for open domain spoken language understandingInterspeech, Singapore, 2014, Unknown, Unknown Region
Conference papers
hal-01194246v1
|
|
Détection et caractérisation d’erreurs dans des transcriptions automatiques pour des systèmes de traduction parole-paroleActes de la conférence JEP 2014, 2014, Le Mans, France
Conference papers
hal-01194239v1
|
|
Multimodal understanding for person recognition in video broadcastsInterspeech, Singapore, 2014, Unknown, Unknown Region
Conference papers
hal-01194244v1
|
|
Multiple-View Constrained Clustering For Unsupervised Face Identification In TV-BroadcastICASSP2014 - Image, Video, and Multidimensional Signal Processing (ICASSP2014 - IVMSP), May 2014, Florence, Italy. pp.494 - 498, ⟨10.1109/ICASSP.2014.6853645⟩
Conference papers
hal-01194240v1
|
|
ASR Error Segment Localization for Spoken Recovery StrategyIEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Vancouver (Canada), 2013, Unknown, Unknown Region
Conference papers
hal-01194252v1
|
|
PERCOLI: a person identification system for the 2013 REPERE challengeSLAM 2013 : First Workshop on Speech, Language and Audio in Multimedia, Aug 2013, Marseille, France. pp.55-60
Conference papers
hal-00834204v1
|
|
Unsupervised Face Identification in TV Content using Audio-Visual Sources11th International Workshop on Content-Based Multimedia Indexing (CBMI 2013), Jun 2013, Veszprém, Hungary. à paraître
Conference papers
hal-00812334v1
|
|
Searching Segments of Interest in Single Story Web-VideosWorkshop on Image and Audio Analysis for Multimedia Interactive Services (WIAMIS), 2013, Unknown, Unknown Region
Conference papers
hal-01194250v1
|
|
Automatic Human Utility Evaluation of ASR Systems: Does WER Really Predict Performance?Interspeech, Lyon (France), 2013, Unknown, Unknown Region
Conference papers
hal-01194248v1
|
|
Can You Give Me Another Word for Hyperbaric?: Improving Speech Translation using Targeted Clarification QuestionsIEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Vancouver (Canada), 2013, Unknown, Unknown Region
Conference papers
hal-01194251v1
|
|
|
Percol0 - un système multimodal de détection de personnes dans des documents vidéo (Percol0 - A multimodal person detection system in video documents) [in French]Actes de la conférence conjointe JEP-TALN-RECITAL 2012, volume 1: JEP, 2012, Grenoble, France. pp.553--560
Conference papers
hal-01194254v1
|
|
Leveraging study of robustness and portability of spoken language understanding systems across languages and domains: the PORTMEDIA corporaThe International Conference on Language Resources and Evaluation, May 2012, Istanbul, Turkey
Conference papers
hal-00683433v1
|
Robustesse et portabilités multilingue et multi-domaines des systèmes de compréhension de la parole : les corpus du projet PortMediaActes de la conférence conjointe JEP-TALN-RECITAL 2012, volume 1: JEP, 2012, Grenoble, France. pp.779--786
Conference papers
hal-01194257v1
|
|
|
Generative Constituent Parsing and Discriminative Dependency Reranking: Experiments on English and FrenchACL 2012 Joint Workshop on Statistical Parsing and Semantic Processing of Morphologically Rich Languages (SP-Sem-MRL 2012), 2012, Jesu Island, South Korea
Conference papers
hal-00702499v1
|
Syntactic annotation of spontaneous speech: application to call-center conversation dataLREC'12, Istambul, Turkey, 2012, Unknown, Unknown Region
Conference papers
hal-01194255v1
|
|
Detecting Person Presence in TV Shows with Linguistic and Structural FeaturesIEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Kyoto (Japan), 2012, Unknown, Unknown Region
Conference papers
hal-01194256v1
|
|
Generative Constituent Parsing and Discriminative Dependency Reranking: Experiments on English and FrenchSP-SEM-MRL 2012, 2012, Unknown, Unknown Region
Conference papers
hal-01194258v1
|
|
|
MACAON : An NLP Tool Suite for Processing Word LatticesACL 2011, 2011, Portland, United States. pp.86-91
Conference papers
hal-00702442v1
|
< StuMaBa>: from deep representation to surfaceProceedings of the 13th European workshop on natural language generation, 2011, Unknown, Unknown Region. pp.232--235
Conference papers
hal-01194264v1
|
|
Applying Multiclass Bandit algorithms to call-type classificationIEEE Automatic Speech Recognition and Understanding Workshop (ASRU'11), 2011, Unknown, Unknown Region
Conference papers
hal-01194262v1
|
|
MACAON:A linguistic tool suite for processing word latticesThe 49th Annual Meeting of the Association for Computational Linguistics: demonstration session, 2011, Unknown, Unknown Region
Conference papers
hal-01194861v1
|
|
MACAON: an NLP tool suite for processing word latticesProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: Systems Demonstrations, 2011, Unknown, Unknown Region. pp.86--91
Conference papers
hal-01194259v1
|
|
LIF at TAC Multiling: Towards a Truly Language Independent SummarizerProc. of the Text Analysis Conference workshop, Gaithersburg, MD (USA), 2011, Unknown, Unknown Region
Conference papers
hal-01194263v1
|
|
TAC2011 MultiLing Pilot OverviewProc. of the Text Analysis Conference workshop, Gaithersburg, MD (USA), 2011, Unknown, Unknown Region
Conference papers
hal-01194265v1
|
|
|
Modèles génératif et discriminant en analyse syntaxique : expériences sur le corpus arboré de Paris 7Traitement Automatique des Langues Naturelles, 2011, Montpellier, France. pp.371--383
Conference papers
hal-00702424v1
|
Modèles génératif et discriminant en analyse syntaxique : expériences sur le corpus arboré de Paris 7TALN'11, Montpellier (France), 2011, Unknown, Unknown Region
Conference papers
hal-01194266v1
|
|
Semi-supervised Part-of-speech Tagging in Speech ApplicationsInterspeech 2010, 2010, Makuhari, Japan
Conference papers
hal-01433898v1
|
|
Evaluation of Semantic Role Labeling and Dependency Parsing of Automatic Speech Recognition OutputIEEE International Conference in Acoustics, Speech and Signal Processing (ICASSP), Dallas (USA), 2010, Unknown, Unknown Region
Conference papers
hal-01194270v1
|
|
Semi-supervised Part-of-speech Tagging in Speech ApplicationsInterspeech, Tokyo (Japan), 2010, Unknown, Unknown Region
Conference papers
hal-01194268v1
|
|
The UMUS system for named entity generation at GREC 2010International Natural Language Generation Conference (INLG), 2010, Unknown, Unknown Region
Conference papers
hal-01194267v1
|
|
Integrating Prosodic Features in Extractive Meeting SummarizationASRU, Merano (Italy), 2009, Unknown, Unknown Region
Conference papers
hal-01194278v1
|
|
Leveraging Sentence Weights in Concept-based Optimization Framework for Extractive Meeting SummarizationInterspeech, Brighton (UK), 2009, Unknown, Unknown Region
Conference papers
hal-01194281v1
|
|
The ICSI/UTD Summarization System at TAC 2009Proc. of the Text Analysis Conference workshop, Gaithersburg, MD (USA), 2009, Unknown, Unknown Region
Conference papers
hal-01194277v1
|
|
Syntactically-informed Models for Comma PredictionProceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taipei, Taiwan, 2009, Unknown, Unknown Region
Conference papers
hal-01194282v1
|
|
Phrase-level and Word-level Strategies for Detecting Appositions in SpeechInterspeech, Brighton (UK), 2009, Unknown, Unknown Region
Conference papers
hal-01194285v1
|
|
ClusterRank: A Graph Based Method for Meeting SummarizationInterspeech, Brighton (UK), 2009, Unknown, Unknown Region
Conference papers
hal-01194284v1
|
|
ICSI-CRF: The Generation of References to the Main Subject and Named Entities Using Conditional Random FieldsACL-IJCNLP, 2009, Unknown, Unknown Region
Conference papers
hal-01194273v1
|
|
|
Combined low level and high level features for Out-Of-Vocabulary Word detectionInterspeech 2009, 2009, Brighton, United Kingdom
Conference papers
hal-01194283v1
|
Any Questions? Automatic Question Detection in MeetingsASRU, Merano (Italy), 2009, Unknown, Unknown Region
Conference papers
hal-01194279v1
|
|
|
Détection de mots hors-vocabulaire par combinaison de mesures de confiance de haut et bas niveauxMajecSTIC 2009 , Nov 2009, Avignon, France
Conference papers
hal-01318077v1
|
A Global Optimization Framework for Meeting SummarizationProceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taipei, Taiwan, 2009, Unknown, Unknown Region
Conference papers
hal-01194280v1
|
|
A Scalable Global Model for SummarizationNAACL/HLT 2009 Workshop on Integer Linear Programming for Natural Language Processing, 2009, Unknown, Unknown Region
Conference papers
hal-01194274v1
|
|
Punctuating Speech for Information ExtractionProceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) Las Vegas, Nevada, 2008, Unknown, Unknown Region
Conference papers
hal-01194289v1
|
|
Efficient Sentence Segmentation Using Syntactic FeaturesSpoken Languge Technologies (SLT), Goa (India), 2008, Unknown, Unknown Region
Conference papers
hal-01194286v1
|
|
A Keyphrase Based Approach to Interactive Meeting SummarizationSpoken Languge Technologies (SLT), Goa (India), 2008, Unknown, Unknown Region
Conference papers
hal-01194292v1
|
|
Packing the Meeting Summarization KnapsackInterspeech, Brisbane (Australia), 2008, Unknown, Unknown Region
Conference papers
hal-01194290v1
|
|
The CALO Meeting Speech Recognition and Understanding SystemSpoken Languge Technologies (SLT), Goa (India), 2008, Unknown, Unknown Region
Conference papers
hal-01194293v1
|
|
The ICSI Summarization System at TAC 2008Proc. of the Text Analysis Conference workshop, Gaithersburg, MD (USA), 2008, Unknown, Unknown Region
Conference papers
hal-01194287v1
|
|
An Analysis of Sentence Segmentation Features for Broadcast News, Broadcast Conversations, and MeetingsProceedings of SIGIR 2007, Searching Spontaneous Conversational Speech (SSCS) workshop, 2007, Unknown, Unknown Region. pp.37-43
Conference papers
hal-01194294v1
|
|
An Interactive Timeline for Speech Database BrowsingInterspeech 2007, Antwerp (Belgium), 2007, Unknown, Unknown Region
Conference papers
hal-01194296v1
|
|
The LIA summarization system at DUC-2007Proceedings of the Document Understanding Workshop (DUC), 2007, Unknown, Unknown Region
Conference papers
hal-01194295v1
|
|
Accès aux connaissances orales par le résumé automatiqueEGC'06, Lille (France), 2006, Unknown, Unknown Region
Conference papers
hal-01194298v1
|
|
The LIA-Thales summarization system at DUC-2006Document Understanding Conference Workshop, HLT-NAACL'06, New York (USA), 2006, Unknown, Unknown Region
Conference papers
hal-01194297v1
|
|
Mining Broadcast News data: Robust Information Extraction from Word LatticesProceeding of Eurospeech'05, Lisboa (Portugal), 2005, Unknown, Unknown Region
Conference papers
hal-01194300v1
|
|
Robust Named Entity Extraction from Spoken ArchivesProceedings of HLT-EMNLP'05, Vancouver (Canada), 2005, Unknown, Unknown Region
Conference papers
hal-01194299v1
|
|
Information retrieval on mixed written and spoken documentsRIAO, Avignon (France), 2004, Unknown, Unknown Region. pp.826-835
Conference papers
hal-01194302v1
|
|
Recherche d'information dans un mélange de documents écrits et parlésJournées d'Etude de la Parole (JEP), Fèz (Morocco), 2004, Unknown, Unknown Region
Conference papers
hal-01194301v1
|
|
Can we predict self-reported customer satisfaction from interactions ?International Conference on Acoustics, Speech and Signal Processing, May 2019, Brighton, United Kingdom
Conference poster
hal-02134252v1
|
Speech onset latencies as an online measure of regularity extractionPoster at Implicit Learning Seminar, Lancaster (UK), 2016, Unknown, Unknown Region. 2016
Conference poster
hal-01454925v1
|
|
|
Combined low level and high level features for Out-Of- Vocabulary Word detectionInterspeech, 2009, Brighton, United Kingdom
Conference poster
hal-02088875v1
|
Finding the Structure of DocumentsZitouni, I. and Bickel, D.M. Multilingual natural language processing applications, IBM Press, pp.21--48, 2011, 978-0137151448
Book sections
hal-01194260v1
|
|
Navigation dans les documents audio par le résumé automatiquePatrice Bellot. Vers une recherche d’information contextuelle, assistée et personnalisée, Hermes, 2011
Book sections
hal-01194261v1
|
|
Speech segmentation and spoken document processingJoseph Olive, Catlin Chrisianson, John McCary. Handbook of Natural Language Processing and Machine Translation, Springer, 2008
Book sections
hal-01194291v1
|
|
Increasing faithfulness in human-human dialog summarization with Spoken Language Understanding tasks2024
Preprints, Working Papers, ...
hal-04699645v1
|
|
Are cascade dialogue state tracking models speaking out of turn in spoken dialogues?2023
Preprints, Working Papers, ...
hal-04267783v1
|
|
Résumé automatique de parole pour un accès efficace aux bases de données audioInterface homme-machine [cs.HC]. Université d'Avignon, 2007. Français. ⟨NNT : ⟩
Theses
tel-00444105v1
|
|
Contextual language understanding Thoughts on Machine Learning in Natural Language ProcessingComputation and Language [cs.CL]. Aix-Marseille Universite, 2019
Habilitation à diriger des recherches
tel-02470185v1
|