Cerisara, Christophe

Research Scientist, CNRS (INS2I)

WG leader

Publications

2025

Conference paper

  1. Linking Industry Sectors and Financial Statements: A Hybrid Approach for Company Classification. Guy Stephane Waffo Dzuyo, Gaël Guibon, Christophe Cerisara, Luis Belmar-Letelier. In proceedings of The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025), Philadelphia (Pennsylvania), United States.

Other publications

  1. Lillama: Large Language Models Compression via Low-Rank Feature Distillation. Yaya Sy, Christophe Cerisara, Irina Illina.

2024

Journal

  1. Few-shot remaining useful life prognostics through auxiliary training with related data-set. Alaaeddine Chaoub, Alexandre Voisin, Christophe Cerisara, Benoît Iung. Neural Computing and Applications, Springer Verlag.

Conference paper

  1. Improving Quotation Attribution with Fictional Character Embeddings. Gaspard Michel, Elena V. Epure, Romain Hennequin, Christophe Cerisara. In proceedings of EMNLP 2024 : The 2024 Conference on Empirical Methods in Natural Language Processing, Miami, United States.
  2. Distinguishing Fictional Voices: a Study of Authorship Verification Models for Quotation Attribution. Gaspard Michel, Elena V. Epure, Romain Hennequin, Christophe Cerisara. In proceedings of 18th Conference of the European Chapter of the Association for Computational Linguistics(.EACL 2024 ) workshop LaTeCH-CLfL, St Julian’s, Malta.

Other publications

  1. Growing Neural Networks have Flat Optima and Generalize Better. Paul Caillon, Christophe Cerisara.

2023

Conference paper

  1. Participation de l’équipe TTGV à DEFT 2023~: Réponse automatique à des QCM issus d’examens en pharmacie. Andréa Blivet, Solène Degrutère, Barbara Gendron, Aurélien Renault, Cyrille Siouffi, Vanessa Gaudray Bouju, Christophe Cerisara, Hélène Flamein, Gaël Guibon, Matthieu Labeau, Tom Rousseau. In proceedings of CORIA TALN RJCRI RECITAL 2023, Paris, France.
  2. SPICE+: Evaluation of automatic audio captioning systems with pre-trained language models. Félix Gontier, Romain Serizel, Christophe Cerisara. In proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2023), Rhodes Island, Greece.

Research report

  1. SlowLLM: large language models on consumer hardware. Christophe Cerisara.

Other publications

  1. Novel-WD: Exploring acquisition of Novel World Knowledge in LLMs Using Prefix-Tuning. Maxime Méloux, Christophe Cerisara.

2022

Conference paper

  1. Towards interpreting deep learning models for industry 4.0 with gated mixture of experts. Alaaeddine Chaoub, Christophe Cerisara, Alexandre Voisin, Benoît Iung. In proceedings of 30th European Signal Processing Conference, EUSIPCO 2022, Belgrade, Serbia.
  2. Deep learning representation pre-training for industry 4.0. Alaaeddine Chaoub, Christophe Cerisara, Alexandre Voisin, Benoît Iung. In proceedings of 7th European Conference of the Prognostics and Health Management Society, PHME22, Turin, Italy.
  3. Risk Analysis for Unsupervised Privacy-Preserving Tools ⋆. Alfredo Cuzzocrea, Christophe Cerisara, Mojtaba Hajian. In proceedings of SEBD’22: 30th Symposium on Advanced Database Systems, Tirrenia (Pisa), Italy.
  4. Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuning. Guillaume Le Berre, Christophe Cerisara, Philippe Langlais, Guy Lapalme. In proceedings of 60th Annual Meeting of the Association for Computational Linguistics, Dublin, Ireland.
  5. Weak supervision for Question Type Detection with large language models. Jiří Martínek, Christophe Cerisara, Pavel Král, Ladislav Lenc, Josef Baloun. In proceedings of INTERSPEECH 2022 -, Incheon, Korea, Republic of.

2021

Conference paper

  1. Growing Neural Networks Achieve Flatter Minima. Paul Caillon, Christophe Cerisara. In proceedings of ICANN 2021 - 30th International Conference on Artificial Neural Networks, Bratislava, Slovakia.
  2. Unsupervised post-tuning of deep neural networks. Christophe Cerisara, Paul Caillon, Guillaume Le Berre. In proceedings of IJCNN, Virtual Event, United States.
  3. Unsupervised Risk for Privacy. Christophe Cerisara, Alfredo Cuzzocrea. In proceedings of IEEE BigData, Special Session on Privacy and Security of Big Data, Orlando (virtual), United States.
  4. Learning representations with end-to-end models for improved remaining useful life prognostic. Alaaeddine Chaoub, Alexandre Voisin, Christophe Cerisara, Benoît Iung. In proceedings of European Conference of the Prognostics and Health Management Society, Virtual event, Italy.
  5. Automated audio captioning by fine-tuning bart with audioset tags. Félix Gontier, Romain Serizel, Christophe Cerisara. In proceedings of DCASE 2021 - 6th Workshop on Detection and Classification of Acoustic Scenes and Events, Virtual, Spain.
  6. Cross-Lingual Approaches for Task-Specific Dialogue Act Recognition. Jiří Martínek, Christophe Cerisara, Pavel Král, Ladislav Lenc. In proceedings of 17th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Hersonissos, Crete, Greece. Ilias Maglogiannis, John Macintyre, Lazaros Iliadis (eds). 2021.

2020

Conference paper

  1. Quality of syntactic implication of RL-based sentence summarization. Hoa Le, Christophe Cerisara, Claire Gardent. In proceedings of AAAI Workshop on Engineering Dependable and Secure Machine Learning Systems 2020, New York, United States.
  2. Seq-to-NSeq model for multi-summary generation. Guillaume Le Berre, Christophe Cerisara. In proceedings of ESANN 2020, Bruges, Belgium.

Other publications

  1. On unsupervised-supervised risk and one-class neural networks. Christophe Cerisara.

2019

Conference paper

  1. RL extraction of syntax-based chunks for sentence compression. Hoa Le, Christophe Cerisara, Claire Gardent. In proceedings of ICANN 2019, Munich, Germany.
  2. Multi-Lingual Dialogue Act Recognition with Deep Learning Methods. Jiří Martínek, Pavel Kral, Ladislav Lenc, Christophe Cerisara. In proceedings of Interspeech 2019, Graz, Austria.
  3. Deep unsupervised system log monitoring. Hubert Nourtel, Christophe Cerisara, Samuel Cruz-Lara. In proceedings of PROFES 2019 - 20th International Conference on Product-Focused Software Process Improvement, Barcelona, Spain.

2018

Journal

  1. On the Effects of Using word2vec Representations in Neural Networks for Dialogue Act Recognition. Christophe Cerisara, Pavel Kral, Ladislav Lenc. Computer Speech and Language, Elsevier.

Conference paper

  1. Multi-task dialog act and sentiment recognition on Mastodon. Christophe Cerisara, Somayeh Jafaritazehjani, Adedayo Oluokun, Hoa Le. In proceedings of COLING, Santa Fe, United States.
  2. Do Convolutional Networks need to be Deep for Text Classification ?. Hoa Le, Christophe Cerisara, Alexandre Denis. In proceedings of AAAI Workshop on Affective Content Analysis, New Orleans, United States.

2017

Research report

  1. Report Transfer Learning of Deep Convolutional Network on Twitter. Hoa Le, Christophe Cerisara, Alexandre Denis.

2016

Conference paper

  1. Weakly-supervised text-to-speech alignment confidence measure. Guillaume Serrière, Christophe Cerisara, Dominique Fohr, Odile Mella. In proceedings of International Conference on Computational Linguistics (COLING), Osaka, Japan.

2015

Conference paper

  1. A Domain Agnostic Approach to Verbalizing n-ary Events without Parallel Corpora. Bikash Gyawali, Claire Gardent, Christophe Cerisara. In proceedings of Proceedings of the 15th European Workshop on Natural Language Generation (ENLG), Brighton, United Kingdom.
  2. Automatic Verbalisation of Biological Events. Bikash Gyawali, Claire Gardent, Christophe Cerisara. In proceedings of International Workshop on Definitions in Ontologies (IWOOD 2015), Lisbon, Portugal.
  3. Semantic Features for Dialogue Act Recognition. Pavel Kral, Ladislav Lenc, Christophe Cerisara. In proceedings of 3rd International Conference on Statistical Language and Speech Processing (SLSP), Budapest, Hungary.
  4. Weakly supervised discriminative training of linear models for Natural Language Processing. Lina Maria Rojas Barahona, Christophe Cerisara. In proceedings of 3rd International Conference on Statistical Language and Speech Processing (SLSP), Budapest, Hungary.
  5. Enhanced discriminative models with tree kernels and unsupervised training for entity detection. Lina Maria Rojas Barahona, Christophe Cerisara. In proceedings of 6th. International Conference on Information Systems & Economic Intelligence (SIIE), Hammamet, Tunisia.

2014

Journal

  1. Automatic dialogue act recognition with syntactic features. Pavel Kral, Christophe Cerisara. Language Resources and Evaluation, Springer Verlag.

Conference paper

  1. Semi-supervised experiments at LORIA for the SPMRL 2014 Shared Task. Christophe Cerisara. In proceedings of Proc. of the Shared Task on Statistical Parsing of Morphologically Rich Languages, Dublin, Ireland.
  2. Semi-supervised SRL system with Bayesian inference. Alejandra Lorenzo, Christophe Cerisara. In proceedings of 15th International Conference on Intelligent Text Processing and Computational Linguistics, Kathmandu, Nepal.
  3. Bayesian Inverse Reinforcement Learning for Modeling Conversational Agents in a Virtual Environment.. Lina Maria Rojas Barahona, Christophe Cerisara. In proceedings of Conference on Intelligent Text Processing and Computational Linguistics, Kathmandu, Nepal.

2013

Book

  1. Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech), 25-29 August 2013, Lyon (France). Frédéric Bimbot, Christophe Cerisara, Cécile Fougeron, Guillaume Gravier, Lori Lamel, François Pellegrino, Pascal Perrier.

Conference paper

  1. Weakly supervised parsing with rules. Christophe Cerisara, Alejandra Lorenzo, Pavel Kral. In proceedings of INTERSPEECH 2013, Lyon, France.
  2. Unsupervised structured semantic inference for spoken dialog reservation tasks. Alejandra Lorenzo, Lina Rojas-Barahona, Christophe Cerisara. In proceedings of SIGDIAL - 14th annual SIGdial Meeting on Discourse and Dialogue - 2013, Metz, France.

2012

Conference paper

  1. Mixed probabilistic and deterministic dependency parsing. Christophe Cerisara, Alejandra Lorenzo. In proceedings of 13th Annual Conference of the International Speech Communication Association - InterSpeech 2012, Portland, United States.
  2. Unsupervised frame based Semantic Role Induction: application to French and English. Alejandra Lorenzo, Christophe Cerisara. In proceedings of Proceedings of the ACL 2012 Joint Workshop on Statistical Parsing and Semantic Processing of Morphologically Rich Languages, Jeju, Korea, Republic of.

2011

Conference paper

  1. Vers la détection des dislocations à gauche dans les transcriptions automatiques du Français parlé / Towards automatic recognition of left dislocation in transcriptions of Spoken French. Corinna Anderson, Christophe Cerisara, Claire Gardent. In proceedings of Traitement Automatique des Langues Naturelles - TALN’2011, Montpellier, France.
  2. The JSafran platform for semi-automatic speech processing. Christophe Cerisara, Claire Gardent. In proceedings of 12th Annual Conference of the International Speech Communication Association - Interspeech 2011, Florence, Italy.
  3. Commas recovery with syntactic features in French and in Czech. Christophe Cerisara, Pavel Kral, Claire Gardent. In proceedings of 12thAnnual Conference of the International Speech Communication Association - Interspeech 2011, Florence, Italy.
  4. Similarity language model. Christian Gillot, Christophe Cerisara. In proceedings of 12thAnnual Conference of the International Speech Communication Association - Interspeech 2011, Florence, Italy.

2010

Journal

  1. Dialogue act recognition approaches. Pavel Kral, Christophe Cerisara. Computing and Informatics, Slovak University Press, Bratislava.

Conference paper

  1. Building and Exploiting a Dependency Treebank for French Radio Broadcast. Christophe Cerisara, Claire Gardent, Corinna Anderson. In proceedings of TLT9 – the ninth international workshop on Treebanks and Linguistic Theories, Tartu, Estonia.
  2. Semi-Automatic Propbanking for French. Claire Gardent, Christophe Cerisara. In proceedings of TLT9 - The Ninth International Workshop on Treebanks and Linguistic Theories, Tartu, Estonia.
  3. Similar N-Gram Language Model. Christian Gillot, Christophe Cerisara, David Langlois, Jean-Paul Haton. In proceedings of INTERSPEECH 2010, Tokyo, Japan.
  4. Memory-Based Active Learning for French Broadcast News. Frédéric Tantini, Christophe Cerisara, Claire Gardent. In proceedings of INTERSPEECH 2010, Tokyo, Japan.

2009

Journal

  1. Automatic discovery of topics and acoustic morphemes from speech. Christophe Cerisara. Computer Speech and Language, Elsevier.
  2. Missing data mask estimation with frequency and temporal dependencies. Sébastien Demange, Christophe Cerisara, Jean-Paul Haton. Computer Speech and Language, Elsevier.

Conference paper

  1. Analyse syntaxique du français parlé. Christophe Cerisara, Claire Gardent. In proceedings of Journée ATALA, Paris, France.
  2. JTrans, an open-source software for semi-automatic text-to-speech alignment. Christophe Cerisara, Odile Mella, Dominique Fohr. In proceedings of Proceedings of the 10th Annual Conference of the International Speech Communication Association - Interspeech 2009, Brighton, United Kingdom.

2008

Conference paper

  1. Exploiting confidence measures for missing data speech recognition. Christophe Cerisara. In proceedings of Proceedings on Acoustics’08, Paris, France.
  2. Evaluation of dialogue act recognition approaches. Pavel Kral, Tomas Pavelka, Christophe Cerisara. In proceedings of IEEE International Workshop on Machine Learning for Signal Processing, Cancun, Mexico.

2007

Journal

  1. On noise masking for automatic missing data speech recognition: a survey and discussion. Christophe Cerisara, Sébastien Demange, Jean-Paul Haton. Computer Speech and Language, Elsevier.
  2. Lexical Structure for Dialogue Act Recognition. Pavel Kral, Christophe Cerisara, Jana Kleckova. Journal of Multimedia, Academy Publisher.

Book chapter

  1. Nouvelles formes d’interaction homme-machine pour l’informatique diffuse. Christophe Cerisara, Yvon Haradji. Marc Dupuis (eds). 2007.

Conference paper

  1. Accurate marginalization range for missing data recognition. Sébastien Demange, Christophe Cerisara, Jean-Paul Haton. In proceedings of INTERSPEECH 2007, Antwerp, Belgium.
  2. Importance of Prosody for Dialogue Acts Recognition. Pavel Kral, Christophe Cerisara, Jana Kleckova. In proceedings of XIIth International Conference “Speech and Computer” - SPECOM’07, Moscou, Russian Federation.
  3. Confidence measures for semi-automatic labeling of dialog acts. Pavel Kral, Christophe Cerisara, Jana Kleckova. In proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP 2007, Honolulu, United States.

2006

Book

  1. Reconnaissance Automatique de la Parole Du signal à son interprétation. Jean-Paul Haton, Christophe Cerisara, Dominique Fohr, Yves Laprie, Kamel Smaïli.
  2. Reconnaissance Automatique de la Parole Du signal à son interprétation. Jean-Paul Haton, Christophe Cerisara, Dominique Fohr, Yves Laprie, Kamel Smaïli.

Conference paper

  1. Evaluation of the SPACE denoising Algorithm on Aurora2. Christophe Cerisara, Khalid Daoudi. In proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Toulouse, France.

  2. An improved version of the SPACE algorithm for noise robust speech recognition. Khalid Daoudi, Christophe Cerisara. In proceedings of IEEE-EURASIP International Symposium on Control, Communications, and Signal Processing, Marrakech, Morocco.

  3. Missing data mask models with global frequency and temporal constraints. Sébastien Demange, Christophe Cerisara, Jean-Paul Haton. In proceedings of Ninth International Conference on Spoken Language Processing - Interspeech 2006 - ICSLP, Pittsburgh, Pennsylvania/USA.

  4. Mask Estimation For Missing Data Recognition Using Background Noise Sniffing. Sébastien Demange, Christophe Cerisara, Jean-Paul Haton. In proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2006, Toulouse/France.

  5. Automatic dialog acts recognition based on sentence structure. Pavel Kral, Christophe Cerisara, Jana Kleckova. In proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP/2006. IEEE (eds). 2006.

  6. Sentence structure for dialog act recognition in Czech. Pavel Kral, Christophe Cerisara, Jana Kleckova, Tomas Pavelka. In proceedings of 2nd IEEE International Conference on Information et Communication Technologies: from Theory to Applications - ICTTA´06.

  7. Automatic Dialog Acts Recognition based on Words Clusters. Pavel Kral, Jana Kleckova, Christophe Cerisara. In proceedings of 9th Western Pacific Acoustics Conference - WESPAC IX 2006.

2005

Conference paper

  1. ANTS le système de transcription automatique du LORIA. Armelle Brun, Christophe Cerisara, Dominique Fohr, Irina Illina, David Langlois, Odile Mella. In proceedings of Worshop ESTER, Avignon, France.
  2. The MAP-SPACE denoising algorithm for noise robust speech recognition. Khalid Daoudi, Christophe Cerisara. In proceedings of IEEE Automatic Speech Recognition and Understanding Workshop - ASRU’2005, San Juan, Puerto Rico, Mexico.
  3. Combination of classifiers for automatic recognition of dialog acts. Pavel Kral, Christophe Cerisara, Jana Kleckova. In proceedings of Proceedings of the 9th European Conference on Speech Communication and Technology - Interspeech - Eurospeech 2005 - Lisbon, Portugal.
  4. Sentence modality recognition in French based on prosody. Pavel Kral, Jana Kleckova, Christophe Cerisara. In proceedings of VI. International Conference on Enformatika, Systems Sciences and Engineering - ESSE 2005.

2004

Journal

  1. Alpha-Jacobian environmental adaptation. Christophe Cerisara, Luca Rigazio, Jean-Claude Junqua. Speech Communication, Elsevier : North-Holland.

Conference paper

  1. ANTS : le système de transcription automatique du Loria. Armelle Brun, Christophe Cerisara, Dominique Fohr, Irina Illina, David Langlois, Odile Mella, Kamel Smaïli. In proceedings of JEP 2004 - 25èmes Journées d’Etude sur la Parole, Fès, Morocco.
  2. Exploiting models intrinsic robustness for noisy speech recognition. Christophe Cerisara, Dominique Fohr, Odile Mella, Irina Illina. In proceedings of 8th International Conference on Spoken Language Processing - ICSLP’2004, Jeju, Corée du Sud.
  3. Experiments on the accuracy of phone models and liaison processing in a French broadcast news transcription system. Dominique Fohr, Odile Mella, Irina Illina, Christophe Cerisara. In proceedings of 8th International Conference on Spoken Language Processing - ICSLP’2004, Jeju, Corée du Sud.
  4. The Automatic News Transcription System: ANTS some Real Time experiments. Irina Illina, Dominique Fohr, Odile Mella, Christophe Cerisara. In proceedings of 8th International Conference on Spoken Language Processing - ICSLP’ 2004, Jeju, Corée du Sud.
  5. Analysis of Importance of the prosodic Features for Automatic Sentence Modality Recognition in French in real Conditions. Pavel Kral, Jana Kleckova, Christophe Cerisara. In proceedings of WSEAS International Conference on Electronics, Control and Signal Processing - ICECS’04, Crete, Greece.

2003

Conference paper

  1. Towards Missing Data Recognition with Cepstral Features. Christophe Cerisara. In proceedings of 8th European Conference on Speech Communication and Technology - EUROSPEECH’03, Geneva, Switzerland.
  2. Robust speech recognition to non-stationary and unpredictable noise based on model-driven approaches. Christophe Cerisara, Irina Illina. In proceedings of 8th European Conference on Speech Communication and Technology - EUROSPEECH’03, Geneva, Switzerland.

2002

Conference paper

  1. Fast Channel and Noise Compensation in the Spectral Domain. Christophe Cerisara, Dominique Fohr. In proceedings of XI European Signal Processing Conference - EUSIPCO 2002, Toulouse, France.
  2. Dynamic estimation of a noise over estimation factor for Jacobian-based adaptation. Christophe Cerisara, Jean-Claude Junqua, Luca Rigazio. In proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2002, Orlando, Florida.
  3. Reconnaissance de la parole pour les locuteurs non natifs en présence de bruit. Dominique Fohr, Odile Mella, Irina Illina, Fabrice Lauri, Christophe Cerisara, Christophe Antoine. In proceedings of XXIVèmes Journées d’Etude sur la Parole - JEP’02, Nancy, France.

2001

Journal

  1. Multi-band automatic speech recognition. Christophe Cerisara, Dominique Fohr. Computer Speech and Language, Elsevier.

Conference paper

  1. Modeling dependency between regression classes in MLLR using multiscale autoregressive models. Christophe Cerisara, Khalid Daoudi. In proceedings of ISCA Workshop on Adaptation methods for speech recognition, Sophia-Antipolis, France.
  2. A comparison of different methods for noise adaptation in a HMM-based speech recognition system. Christophe Cerisara, Dominique Fohr, Irina Illina, Fabrice Lauri, Odile Mella. In proceedings of International Congress on Acoustics, Italy, Rome.
  3. Environmental adaptation based on first order approximation. Christophe Cerisara, Luca Rigazio, Robert Boman, Jean-Claude Junqua. In proceedings of International Conference on Acoustics, Speech, and Signal Processing - ICASSP 2001, Salt lake City, USA.
  4. Environment-adaptive algorithms for robust speech recognition. Jean-Claude Junqua, Christophe Cerisara, Luca Rigazio, David Kryze. In proceedings of International Workshop on Hands-Free Speech Communication - HSC 2001, Kyoto, Japan.

2000

Conference paper

  1. Asynchrony in Multi-Band Speech Recognition. Christophe Cerisara, Dominique Fohr, Jean-Paul Haton. In proceedings of IEEE International Conference on Acoustics, Speech, & Signal Processing - ICASSP’2000, Istanbul, Turkey.
  2. Transformation of Jacobian matrices for noisy speech recognition. Christophe Cerisara, Luca Rigazio, Robert Boman, Jean-Claude Junqua. In proceedings of ICSLP’2000, none.

1999

Book chapter

  1. Dealing With Loss of Synchronism in Multi-Band Continuous Speech Recognition Systems. Christophe Cerisara. none (eds). 1999.

Conference paper

  1. Robust behavior of multi-band paradigm. Christophe Cerisara, Dominique Fohr, Jean-Paul Haton. In proceedings of Robust Methods for Speech Recognition in Adverse Conditions, Tampere, Finland.
  2. Towards a Global Optimization Scheme for Multi-Band Speech Recognition. Christophe Cerisara, Jean-Paul Haton, Dominique Fohr. In proceedings of 6th European Conference on Speech Communication & Technology - EUROSPEECH’99, Budapest, Hungary.
  3. Improvement of Multi-Band Speech Recognition. Jean-Paul Haton, Christophe Cerisara, Dominique Fohr. In proceedings of International Workshop Speech & Computer - SPECOM’99, Moscow, Russia.
Back to top