Kamel Smaïli
Présentation
Publications
Publications
|
|
Modeling North African Dialects from Standard LanguagesThe Third Arabic Natural Language Processing Conference, Nov 2025, Suzhou, China |
|
|
Boosting Fake News Detection in Arabic Dialects with Consistency-Aware LLM Merging Techniques6th International Conference on Natural Language Processing and Computational Linguistics (NLPCL 2025), Sep 2025, Toronto ( CA ), Canada. pp.25 - 33, ⟨10.5121/csit.2025.151803⟩ |
|
|
ABDUL: a new Approach to Build language models for Dialects Using formal Language corpora onlyNAACL 2025 Workshop on Language Models for Underserved Communities, ACL, Apr 2025, Albuquerque, United States |
|
|
Knowledge Distillation for Efficient Algerian Dialect Processing: Training Compact BERT Models with DziriBERT7th International Conference on Advances in Signal Processing and Artificial Intelligence, Apr 2025, Innsbruck (Austria), Austria |
|
|
Fake News Detection via Intermediate-Layer Emotional RepresentationsCompanion Proceedings of the ACM on Web Conference 2025, Association for Computing Machinery, Apr 2025, Sydney, Australia. pp.2680-2684, ⟨10.1145/3701716.3717537⟩ |
|
|
Tarab Music in the Era of Artificial Intelligence: Our experience in research, development, and capacity-building in higher education (Presentation abstract)Arab Music Festival and Conference, Cairo Opera House, Egypt, Oct 2024, Cairo, Egypt |
|
|
Towards A Neural Machine Translation Proposal to Help Everyday Communication for People with Broca's AphasiaNew Trends in Translation and Technology, Jul 2024, Varna, Bulgaria |
|
|
Detecting Fake News: Exploring Key Features in Multilingual Arabic Dialect CorpusThe 8th International Conference on Arabic Language Processing, Apr 2024, RABAT, Morocco |
|
|
BOUTEF: Bolstering Our Understanding Through an Elaborated Fake News CorpusThe 8th International Conference on Arabic Language Processing, Apr 2024, RABAT, Morocco |
|
|
How can machine translation help generate Arab melodic improvisation?The 24th Annual Conference of The European Association for Machine Translation (EAMT 2023°, Jun 2023, TEMPERE, Finland |
|
|
Supervised contrastive learning as multi-objective optimization for fine-tuning large pre-trained language modelsIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), Jun 2023, Rhodès, Greece |
|
|
Language rehabilitation of people with BROCA aphasia using deep neural machine translationFifth International Conference on Computational Linguistics in Bulgaria, Sep 2022, Sofia, Bulgaria |
|
|
Offline Corpus Augmentation for English-Amharic Machine Translation2022 The 5th International Conference on Information and Computer Technologies, Mar 2022, New York, United States |
|
|
A Deep Convolution Generative Adversarial Network for the Production of Images of Human FacesACIIDS 2022 - 14th Asian Conference on Intelligent Information and Database Systems, Nov 2022, Ho Chi Minh, Vietnam |
|
|
SimSCL: A Simple fully-Supervised Contrastive Learning Framework for Text RepresentationAJCAI 2021 - 34th Australasian Joint Conference on Artificial Intelligence, Feb 2022, Sydney, Australia |
|
|
ACQAD: A Dataset for Arabic Complex Question AnsweringInternational Conference on Cyber Security, Artificial Inteligence and Theoretical Computer Science, Dec 2022, Boumerdès, Algeria |
|
|
The only chance to understand: machine translation of the severely endangered low-resource languages of EurasiaThe Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT), COLING 2022, Oct 2022, Gyeongju, South Korea |
|
|
Improving Machine Translation of Arabic Dialects through Multi-Task Learning20th International Conference Italian Association for Artificial Intelligence:AIxIA 2021, Dec 2021, MILAN/Virtual, Italy |
|
|
Parallel Corpora Preparation for English-Amharic Machine TranslationIWANN 2021 - International Work on Artificial Neural Networks, Conference Springer LNCS proceedings, Jun 2021, Online, Spain |
|
|
Investigating data sharing in speech recognition for an underresourced language: the case of algerian dialect7th International Conference on Natural Language Processing - NATP 2021, Mar 2021, Vienna, Austria |
|
|
Predicting and Critiquing Machine Virtuosity: Mawwal Accompaniment as Case StudyInternational Computer Music Conference, Jul 2021, Santiago, Chile |
|
|
Creating multi-scripts sentiment analysis lexicons for Algerian, Moroccan and Tunisian dialects7th International Conference on Data Mining (DTMN 2021) Computer Science Conference Proceedings in Computer Science & Information Technology (CS & IT), Sep 2021, Copenhagen, Denmark |
|
|
CESAR: A new metric to measure the level of code-switching in corpora -Application to Maghrebian dialectsIntelliSys2021, Sep 2021, Amsterdam, Netherlands |
|
|
Improving the Community Question Retrieval Performance Using Attention-based Siamese LSTMNLDB2020: 25th International Conference on Natural Language & Information Systems, Jun 2020, Saarbrücken, Germany |
|
|
Projet AMIS : résumé et traduction automatique de vidéos6e 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, Jun 2020, Nancy, France. pp.53-56 |
|
|
Analyse de sentiments des vidéos en dialecte algérien6e 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, 2020, Nancy, France. pp.296-304 |
|
|
Enhancing Question Retrieval in Community Question Answering Using Word EmbeddingsEnhancing Question Retrieval in Community Question Answering Using Word Embeddings: Proceedings of the 23rd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems KES2019, Sep 2019, Budapest, Hungary |
|
|
Manhattan Siamese LSTM for Question Retrieval in Community Question AnsweringThe 18th International Conference on Ontologies, DataBases, and Applications of Semantics, Oct 2019, Rhodès, Greece |
|
|
Extractive Text-Based Summarization of Arabic videos: Issues, Approaches and EvaluationsICALP: International Conference on Arabic Language Processing, Oct 2019, Nancy, France. pp.65-78, ⟨10.1007/978-3-030-32959-4_5⟩ |
|
|
The SMarT Classifier for Arabic Fine-Grained Dialect IdentificationThe Fourth Arabic Natural Language Processing Workshop co-located with ACL, Aug 2019, Florence, Italy |
|
|
Machine Translation on a parallel Code-Switched CorpusCanadian AI 2019 - 32nd Conference on Canadian Artificial Intelligence, May 2019, Ontario, Canada |
|
|
A Fine-grained Multilingual Analysis Based on the Appraisal Theory: Application to Arabic and English VideosICALP: International Conference on Arabic Language Processing, Oct 2019, Nancy, France. pp.49-61, ⟨10.1007/978-3-030-32959-4_4⟩ |
|
|
A Proposed Methodology for Subjective Evaluation of Video and Text SummarizationMISSI 2018 - 11th edition of the International Conference on Multimedia and Network Information Systems, Sep 2018, Wrocław, Poland. pp.396-404, ⟨10.1007/978-3-319-98678-4_40⟩ |
|
|
An Automatic Learning of an Algerian Dialect Lexicon by using Multilingual Word Embeddings11th edition of the Language Resources and Evaluation Conference, LREC 2018, May 2018, Miyazaki, Japan |
|
|
PADIC: extension and new experiments7th International Conference on Advanced Technologies ICAT, Apr 2018, Antalya, Turkey |
|
|
An Integrated AMIS Prototype for Automated Summarization and Translation of Newscasts and ReportsMISSI 2018 - 11th International Conference on Multimedia and Network Information Systems, Sep 2018, Wroclaw, Poland. pp.415-423, ⟨10.1007/978-3-319-98678-4_42⟩ |
|
|
A First Summarization System of a Video in a Target LanguageMISSI 2018 - 11th edition of the International Conference on Multimedia and Network Information Systems, Sep 2018, Wrocław, Poland. pp.1-12 |
|
|
Is statistical machine translation approach dead?ICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, ISGA, Dec 2017, Casablanca, Morocco. pp.1-5 |
|
|
A Word Embedding based Method for Question Retrieval in Community Question AnsweringICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, ISGA, Dec 2017, Casablanca, Morocco |
|
|
An empirical study of the Algerian dialect of Social networkICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, Dec 2017, Casablanca, Morocco |
|
|
GAWO: Genetic-based optimization algorithm for SMTICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, ISGA, Dec 2017, Maroc, Morocco |
|
|
Maghrebi Arabic dialect processing: an overviewICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, ISGA, Dec 2017, Casablanca, Morocco |
|
|
An enhanced automatic speech recognition system for ArabicThe third Arabic Natural Language Processing Workshop - EACL 2017, Apr 2017, Valencia, Spain |
|
|
Creating Parallel Arabic Dialect Corpus: Pitfalls to Avoid18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLING), Apr 2017, Budapest, Hungary |
|
|
About vocabulary adaptation for automatic speech recognition of video dataICNLSSP'2017 - International Conference on Natural Language, Signal and Speech Processing, Dec 2017, Casablanca, Morocco. pp.1-5 |
|
|
How to match bilingual tweets ?6th NLP 2017 - Computer Science Conference Proceedings in Computer Science & Information Technology (CS & IT) , Feb 2017, Sydney, Australia |
|
|
CALYOU: A Comparable Spoken Algerian Corpus Harvested from YouTube18th Annual Conference of the International Communication Association (Interspeech), Aug 2017, Stockholm, Sweden |
|
|
Statistical Machine Translation from Arab Vocal Improvisation to Instrumental Melodic AccompanimentICNLSSP 2017 - International Conference on Natural Language, Signal and Speech Processing, ISGA, Dec 2017, Casablanca, Morocco |
|
|
Development of the Arabic Loria Automatic Speech Recognition system (ALASR) and its evaluation for Algerian dialectACLing 2017 - 3rd International Conference on Arabic Computational Linguistics, Nov 2017, Dubai, United Arab Emirates. pp.1-8 |
|
|
Measuring the comparability of multilingual corpora extracted from Twitter and othersHrTAL2016 - Tenth International Conference on Natural Language Processing, Sep 2016, Dubrovnik, Croatia |
Definition of Requirements for Accessing Multilingual Information and OpinionsThe 10th edition of International Conference on Multimedia & Network Information Systems, Sep 2016, WROCLAW, Poland |
|
|
|
Cross-Dialectal Arabic ProcessingInternational Conference on Intelligent Text Processing and Computational Linguistics, Apr 2015, cairo, Egypt. ⟨10.1007/978-3-319-18111-0_47⟩ |
|
|
STATISTICAL MACHINE TRANSLATION IMPROVEMENT BASED ON PHRASE SELECTIONRecent Advances in Natural Language Processing, Sep 2015, Hissar, Bulgaria |
|
|
Machine Translation Experiments on PADIC: A Parallel Arabic DIalect CorpusThe 29th Pacific Asia Conference on Language, Information and Computation, Oct 2015, shanghai, China |
|
|
Building Resources for Algerian Arabic Dialects15th Annual Conference of the International Communication Association Interspeech, ISCA, Sep 2014, Singapour, Singapore |
|
|
Building and Modelling Multilingual Subjective CorporaProceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), May 2014, Reykjavik, Iceland, Iceland |
|
|
Clustering and Classification of Like-Minded People from Their TweetsCOOL-SNA Workshop on Connecting Online and Offline Social Network Analysis' of the IEEE International Conference on Data Mining (ICDM'14), Dec 2014, Shenzen, China |
|
|
Cross-Lingual Semantic Similarity Measure for Comparable ArticlesAdvances in Natural Language Processing - 9th International Conference on NLP, PolTAL 2014, Warsaw, Poland, September 17-19, 2014. Proceedings, Sep 2014, Warsaw, Poland. pp.105--115, ⟨10.1007/978-3-319-10888-9_11⟩ |
|
|
Training phrase-based SMT without explicit word aligment15th International Conference on Intelligent Text Processing and Computational Linguistics, Apr 2014, Kathmandu, Nepal. pp.233-241 |
|
|
Phrase-based Language Modelling for Statistical Machine Translation11th International Workshop on Spoken Language, Dec 2014, Lake Tahoe, United States |
|
|
Grapheme To Phoneme Conversion - An Arabic Dialect CaseSpoken Language Technologies for Under-resourced Languages, May 2014, Saint Petesbourg, Russia |
|
|
Comparing Multilingual Comparable Articles Based On OpinionsProceedings of the 6th Workshop on Building and Using Comparable Corpora, Association for Computational Linguistics ACL, Aug 2013, Sofia, Bulgaria. pp.105-111 |
|
|
Diacritics Restoration for Arabic DialectsINTERSPEECH 2013 - 14th Annual Conference of the International Speech Communication Association, ISCA, Aug 2013, Lyon, France |
|
|
LORIA System for the WMT13 Quality Estimation Shared TaskACL 2013 - Eighth Workshop on Statistical Machine Translation, Aug 2013, Sofia, Bulgaria. pp.380 - 385 |
|
|
LORIA System for the WMT12 Quality Estimation Shared TaskNAACL 2012 - The Seventh Workshop on Statistical Machine Translation, Jun 2012, Montréal, Canada. pp.114--119 |
|
|
A Study of a Non-Resourced Language: The Case of one of the Algerian DialectsThe third International Workshop on Spoken Languages Technologies for Under-resourced Languages - SLTU'12, May 2012, Cape-town, South Africa. pp.1-7 |
|
|
A new method for learning Phrase Based Machine Translation with Multivariate Mutual InformationThe 8th International Conference on Natural Language Processing and Knowledge Engineering - NLP-KE'12, Sep 2012, HuangShan, China |
|
|
Training Statistical Machine Translation with Multivariate Mutual Information5th Language and Technology Conference, Nov 2011, Poznan, Poland |
|
|
Broadcast news speech-to-text translation experimentsThe Thirteenth Machine Translation Summit, Sep 2011, Xiamen, China. pp.378-381 |
Cleaning statistical language models3d. International Conference on Information Systems and Economic Intelligence (SIIE'2010), Feb 2010, Sousse, Tunisia |
|
Utilisation de graphes sémantiques pour l'extraction et la traduction des idées essentielles d'un texte en langue étrangère10ième Conférence Internationale Francophone sur l'Extraction et la Gestion des Connaissances - EGC 2010, Jan 2010, Hammamet, Tunisie. pp.687-688 |
|
|
|
Multi-Category Support Vector Machines for Identifying Arabic Topics10th International Conference on Intelligent Text Processing and Computational Linguistics - CICLing 2009, Mar 2009, Mexico, Mexico |
|
|
Efficient Combination of Confidence Measures for Machine Translation10th Annual Conference of the International Speech Communication Association - INTERSPEECH 2009, Sep 2009, Brighton, United Kingdom |
|
|
Comparative study of Arabic and french statistical language modelsICAART'09 - International Conference On agents and Artificial Intelligence, INSTICC, Jan 2009, Porto, Portugal |
|
|
Identifying Conflicts Through Emails by Using an Emotion Ontology6th International Workshop on Natural Language Processing and Cognitive Science Collocated with 11th International Conference on Enterprise Information Systems (ICEIS 2009), May 2009, Milano, Italy |
|
|
Comparing TR-Classifier and KNN by using Reduced Sizes of Vocabularies3rd International Conference on Arabic Language Processing, May 2009, Rabat, Morocco |
|
|
Word- and sentence-level confidence measures for machine translation13th Annual Meeting of the European Association for Machine Translation - EAMT 09, May 2009, Barcelona, Spain |
|
|
New Confidence Measures for Statistical Machine TranslationInternational Conference On Agents and Artificial Intelligence - ICAART 09, Jan 2009, Porto, Portugal |
|
|
Discovering Phrases in Machine Translation by Simulated AnnealingINTERSPEECH 2008 - 9th Annual Conference of the International Speech Communication Association, Sep 2008, Brisbane, Australia. pp.2354-2357 |
|
|
Une alternative aux modèles de traduction statistique d'IBM : Les triggers inter-langues15eme conférence sur le Traitement Automatique des Langues Naturelles - TALN'08, Jun 2008, Avignon, France |
|
|
Phrase-Based Machine Translation based on Simulated AnnealingSixth international conference on Language Resources and Evaluation - LREC 2008, May 2008, Marrakech, Morocco |
|
|
Arabic statistical language modeling9es Journées internationales d'Analyse statistique des Données Textuelles - JADT 2008, Mar 2008, Lyon, France. pp.837-844 |
|
|
Conflict Ontology Enrichment Based on TriggersThe 2nd International workshop on Ontologies and Information Systems for the Semantic Web, ACM 17th Conference on Information and Knowledge Management, Oct 2008, Napa Valley, California, United States |
Constitution d'un corpus de la langue Arabe à partir du WebColloque International sur le Traitement Automatique de la Langue Arabe - CITALA'07, Oct 2007, Rabat, Maroc |
|
|
|
Building a bilingual dictionary from movie subtitles based on inter-lingual triggersTranslating and the Computer, Nov 2007, Londres, United Kingdom |
|
|
Building Parallel Corpora from MoviesThe 4th International Workshop on Natural Language Processing and Cognitive Science - NLPCS 2007, Jun 2007, Funchal, Madeira, Portugal |
|
|
Improving language models by using distant informationInternational Symposium on Signal Processing and its Applications - ISSPA 2007, Feb 2007, Sharjah, United Arab Emirates |
|
|
Using inter-lingual triggers for Machine translation8th Annual Conference of the International Speech Communication Association - INTERSPEECH 2007, Aug 2007, Antwerp, Belgium. pp.2829-2832 |
|
|
Linguistic features modeling based on Partial New CacheInternational Conference on Language Resources and Evaluation - LREC 2006, May 2006, Magazzini del Cotone Conference Center, Genoa/ITALY |
|
|
How to handle gender and number agreement in statistical language models?Ninth International Conference on Spoken Language Processing - INTERSPEECH 2006, Sep 2006, Pittsburgh, Pennsylvania/USA |
Exploration et utilisation d'informations distantes dans les modèles de langage statistiques13ème Conférence sur le Traitement Automatique des Langues Naturelles - TALN'2006, Apr 2006, Leuven, Belgique. pp.425-434 |
|
|
|
Rethinking Language Models within the Framework of Dynamic Bayesian Networks18th Conference of the Canadian Society for Computational Studies of Intelligence, Canadian AI 2005, May 2005, Victoria, Canada. pp.432-437 |
|
|
Comparison of Topic Identification methods for Arabic LanguageInternational Conference on Recent Advances in Natural Language Processing - RANLP 2005, Sep 2005, Borovets, Bulgaria |
|
|
From speech to SQL queries : a speech understanding systemThe twentieth national Conference on Artificial Intelligence workshop on spoken language understanding, 2005, Pittsburg, United States |
|
|
ANTS : le système de transcription automatique du LoriaJEP 2004 - 25èmes Journées d'Etude sur la Parole, Apr 2004, Fès, Maroc. pp.4 |
|
|
Une nouvelle approche de modélisation du langage par des réseaux Bayésiens dynamiquesXXVes Journées d'Etudes sur la Parole - JEP-TALN-RECITAL 2004, 2004, Fès, Maroc |
|
|
Fiabilité de la référence humaine dans la détection de thèmeTraitement Automatique des Langues Naturelles - TALN'2004, Apr 2004, Fès, Maroc. 10 p |
|
|
Statistical Feature Language Model8th International Conference on Spoken Language Processing - ICSLP' 2004, 2004, Jeju, South Korea. 4 p |
|
|
Un système de compréhension automatique de la parole pour l'interrogation orale d'une base de données de bourseJournées d'Etudes sur la Parole - JEP'04, 2004, Fès, Maroc. 4 p |
A complete understanding speech system based on semantic concepts4th International Conference on Language Resources and Evaluation - LREC'04, May 2004, Lisbonne, Portugal, 4 p |
|
|
|
Language modeling using dynamic Bayesian networks4th International Conference on Language Resources and Evaluation - LREC 2004, 2004, Lisbonne, Portugal |
|
|
Understanding speech based on a Bayesian concept extraction methodSixth International Conference on Text Speech and Dialogue - TSD'03, Sep 2003, Ceské-Budejovic, République Tchèque, France. 8 p |
|
|
Understanding process for speech recognitionEighth European Conference on Speech Communication and Technology - EuroSpeech'03, Sep 2003, Genève, Suisse, France. 4 p |
|
|
Efficient linear combination for distant n-gram models8th European Conference on Speech Communication and Technology - Eurospeech'03, Sep 2003, Genève, Switzerland. pp.409-412 |
|
|
Nouvelle approche de la sélection de vocabulaire pour la détection de thèmeTraitement Automatique du Langage Naturel - TALN'2003, 2003, Batz-sur-Mer, France, 10 p |
Vers la compréhension automatique de la parole : extraction des concepts par réseaux bayésiensDixième Conférence en Traitement Automatique des Langues Naturelles - TALN'03, Jun 2003, Batz-sur-Mer, France, 10 p |
|
|
|
Description d'un système de compréhension automatique de la paroleTroisièmes Ateliers en Traitement et Analyse d'Images : Méthodes et Applications - TAIMA'03, Oct 2003, Hammamet, Tunisie, France. 6 p |
Dynamic Topic Identification : Introduction of Trigger pairs in the Cache ModelInternational Workshop Speech and Computer 2002 - SPECOM'2002, 2002, St-Petersburg, Russia, 4 p |
|
Retrieving phrases by selecting the history: application to Automatic Speech Recognition7th International Conference on Spoken Language Processing - ICSLP'2002, Sep 2002, Denver, USA, pp.721 |
|
|
|
Identification thématique hiérarchique : Application aux forums de discussions9ème conférence annuelle sur le Traitement Automatique des Langues Naturelles - TALN'02, Jun 2002, Nancy, France. pp.24 - 27 |
|
|
Détection de séquences par sélection de l'historique : application à la reconnaissance automatique de la paroleXXIVe Journées d'Etudes sur la Parole - JEP'2002, Jun 2002, Nancy, France, pp.301 |
WSIM : une méthode de détection de thème fondée sur la similarité entre motsTraitement Automatique des Langues Naturelles - TALN'2002, Jun 2002, Nancy, France, 10 p |
|
|
|
Neural Network and Information Theory In Automatic Speech UnderstandingSPECOM 2002 - International Workshop Speech and Computer, 2002, St-Petersburg, Russia. pp.1-4 |
Contribution to Topic Identification by Using Word Similarity7th International Conference on Spoken Language Processing - ICSLP'2002, Sep 2002, Denver, Colorado, USA, 4 p |
|
Statistical Language Model based on a Hierarchical Approach : MCnv7th european conference on speech communication and technology - EUROSPEECH 2001, 2001, Aalborg, Denmark, pp.29 |
|
A New Method Based on Context for Combining Statistical Language ModelsThird International Conference on Modeling and Using Context - CONTEXT 01, 2001, Dundee, Scotland, pp.235-247 |
|
Improving Statistical Language Models by Removing Impossible EventsProceedings of the International Workshop "Speech and Computer" - SPECOM 2001, 2001, Moscow, Russia, 4 p |
|
Efficient Language Models Combination: Application to Phrase FindingProceedings of the International Workshop "Speech and Computer" - SPECOM 2001, 2001, Moscow, Russia, 4 p |
|
Dynamic Topic Identification: Towards Combination of MethodsRecent Advances in Natural Language Processing - RANLP'2001, Galia Angelova, Kalima Bontcheva, Ruslan Mitkov, Nicolas Nicolov, Nikolai Nikolov, 2001, Tzigov Chark, Bulgaria, pp.255-257 |
|
|
|
A comparative study of Topic Identification on Newspaper and E-mailProceedings of the 8th International Symposium on String Processing and Information Retrieval - SPIRE'01, 2001, Laguna de San Rafael, Chili, pp.238-241 |
|
|
A Hierarchical Approach for Topic IdentificationProceedings of the international workshop Speech and Computer - SPECOM'01, Nov 2001, Moscow, Russia, France. 4 p |
|
|
Discarding Impossible Events from Statistical Language ModelsInternational Conference on Spoken Language Processing, Oct 2000, Pékin, China, 4 p |
|
|
Vers une meilleure modélisation du langage : la prise en compte des séquences dans les modèles statistiquesXXIIIèmes Journées d'Etude sur la Parole - JEP'2000, 2000, Aussois, France, 4 p |
|
|
Experiment Analysis in Newspaper Topic DetectionSPIRE 2000 - String Processing & Information Retrieval, 2000, A Coruna, Spain. pp.55 - 64 |
Topic Identification Challenge Based on Short Word HistoryTraitement Automatique du Langage Naturel - TALN'00, 2000, Lausanne, Suisse, pp.383-392 |
|
|
|
Variable-Length Class Sequences Based on a Hierarchical Approach: MCnvSCI 2000 - 4th Word Multiconference on Systemics, Cybertinics & Informatics, Jul 2000, Orlando, United States. pp.6 |
|
|
Dealing with distant relationships in natural language modelling for automatic speech recognition4th World Multiconference on Systemics, Cybernetics & Informatics - SCI'2000, International Institute of Informatics & Systemics, 2000, Orlando, USA, pp.400-405 |
|
|
Beyond the Conventional Statistical Language Models: The Variable-Length Sequences ApproachInternational Conference on Speech Language Processing, 2000, Pékin, China. pp.4 |
A New Based Distance Language Model for a Dictation Machine: application to MAUD6th European Conference on Speech Communication & Technology - EUROSPEECH'99, 1999, Budapest, Hungary, pp.1779-1782 |
|
|
|
Variable-Length Sequence Language Model for Large Vocabulary Continuous Dictation Machine6th European Conference on Speech Communication and Technology - EUROSPEECH'99, 1999, Budapest, Hungary |
Automatic and manual clustering for large vocabulary speech recognition: a comparative study6th European Conference on Speech Communication & Technology - EUROSPEECH'99, 1999, Budapest, Hungary, 4 p |
|
Towards a Better Collaboration Between a n-class and a n-gram Language ModelSPECOM, Oct 1999, Moscow, Russia |
|
|
|
A first evaluation campaign for language modelsFirst international conference on language resources and evaluation, May 1998, Grenade, Spain |
Variable-length class sequences based on a hierarchical approach: MCnvSPECOM 1998 - 3rd International Workshop on Speech and Computer, Oct 1998, Saint-Petersbourg, Russia |
|
|
|
A COMPARATIVE STUDY BETWEEN POLYCLASS AND MULTICLASS LANGUAGE MODELSProceedings of the Fifth International Conference on Spoken Language Processing, 1998, Sydney, Australia |
An Hybrid Language Model for a Continuous Dictation Prototype5th European Conference on Speech Communication and Technology, Sep 1997, Rhodes, Greece |
|
|
|
Towards an oral interface for data entry: The MAUD SystemEuropean Research Consortium for Informatics and Mathematics User Interfaces for AII, 1997, Nancy, France |
|
|
A new algorithm for Automatic Word Classification based on an Improved Simulated Annealing TechniqueThe 5th International Conference on the Cognitive Science of Natural Language Processing, 1996, Dublin, Ireland |
Which model for future speech recognition systems: Hidden Markov models for finite-state automata?IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP-94, 1994, Adelaïd, Australia. pp.633-635 |
|
MAUD : Une interface vocale pour la saisie de textes lus2nd International conference Interface to real and virtual worlds, Mar 1993, Montpellier, France. pp.311-318 |
|
Integration of phonological knowledge in a continuous speech recognition systemEuropean conference on speech communication and technology, Sep 1993, Berlin, Germany. pp.2191-2194 |
|
|
|
La composante lexicale de la machine à dicter MAUD,Séminaire Lexique, Jan 1992, Toulouse, France. pp.71-82 |
|
|
Restrictions sémantiques apportées à l'étude des groupes nominaux en 'NdeN' : application à la machine à dicter19èmes Journées d'Etudes sur la Parole, 1992, Bruxelles, Belgique |
|
|
A continuous speech recognition approach for the design of a dictation machineEuropean Conference on Speech Technology, 1991, Genova, Italy. pp.953-956 |
Idées et concepts de réalisation d'une machine à dicter destinée aux grands vocabulairesXVIIIèmes journées d'études sur la parole, May 1990, Montréal, Canada. pp.337-341 |
|
Statistical methods in multi-speaker automatic speech recognitionASMDA - 4th International Symposium on Applied stochastic models and data analysis - 1988, 1988, Nancy, France |
|
|
Evaluation of Improved Components of AMIS Project for Speech Recognition, Machine Translation and Video/Audio/Text SummarizationMultimedia Communications, Services and Security, pp.320-331, 2020, 978-3-030-58999-8. ⟨10.1007/978-3-030-59000-0_24⟩ |
|
|
An Arabic Corpus of Fake News: Collection, Analysis and ClassificationArabic Language Processing: From Theory to Practice 7th International Conference, ICALP 2019, Nancy, France, October 16–17, 2019, Proceedings, Communications in Computer and Information Science book series (CCIS, volume 1108), pp.292-302, 2019, ⟨10.1007/978-3-030-32959-4_21⟩ |
|
|
Automatic identification methods on a corpus of twenty five fine-grained Arabic dialectsArabic Language Processing: From Theory to Practice 7th International Conference, ICALP 2019, Nancy, France, October 16–17, 2019, Proceedings, Communications in Computer and Information Science book series (CCIS, volume 1108), 2019, ⟨10.1007/978-3-030-32959-4_6⟩ |
|
|
Genetic-based Decoder for Statistical Machine TranslationSpringer LNCS series, Lecture Notes in Computer Science, 2016 |
|
|
Grouping Like-Minded Users for Ratings’ PredictionIntelligent Decision Technologies, 2016, 978-3-319-39629-3 |
|
|
A new language model based on possibility theorySpringer LNCS series, Lecture Notes in Computer Science., 2016 |
|
|
MAUD : Un prototype de machine à dicter vocalenone. Ressources et évaluation en ingénierie des langues, De Boeck, pp.315-328, 2000, universités francophones |
Supervised Contrastive Learning as Multi-Objective Optimization for Fine-Tuning Large Pre-trained Language Models2022 |
|
|
Projet RAIVES (Recherche Automatique d'Informations Verbales Et Sonores) vers l'extraction et la structuration de données radiophoniques sur Internet[Contrat] A02-R-553 || parlangeau-valles02a, IRIT - Institut de recherche en informatique de Toulouse; LORIA (Université de Lorraine, CNRS, INRIA). 2002 |
Comparaison d'un réseau de neurones artificiel et d'une méthode statistique pour la classification sémantique[Interne] A02-R-034 || jamoussi02a, 2002, 10 p |
|
|
|
Reconnaissance automatique de la parole en présence de bruit pour une application grand public[Research Report] CNRS. 1995 |
Conception et réalisation d'une machine à dictée à entrée vocale destinée aux grands vocabulaires : le système MaudAutre. Université Henri Poincaré - Nancy 1, 1991. Français. ⟨NNT : 1991NAN10244⟩ |