Research

Put at scale cutting edge NLP approaches

---

Publications

See details on:

• google scholar: http://scholar.google.fr/citations?user=7gC6CXoAAAAJ
• and on HAL: https://cv.archives-ouvertes.fr/servan

2024

• Pierre Lepagnol, Thomas Gerald, Sahar Ghannay, Christophe Servan, Sophie Rosset. Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification. In The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, TURIN, Italy . [PDF]
• Nadège Alavoine, Gaëlle Laperrière, Christophe Servan, Sahar Ghannay, Sophie Rosset. Nouvelle tâche sémantique pour le corpus de compréhension de parole en français MEDIA. 35èmes 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.470-480 . [PDF]
• Pierre Lepagnol, Thomas Gerald, Sahar Ghannay, Christophe Servan, Sophie Rosset. Les petits modèles sont bons : une étude empirique de classification dans un contexte zero-shot. In 35èmes 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.113-129 . [PDF]
• Christophe Servan, Sahar Ghannay, Sophie Rosset. mALBERT: Is a Compact Multilingual BERT Model Still Worth It?. In The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, Torino, Italy . [PDF]
• Nesrine Bannour, Christophe Servan, Aurélie Névéol, Xavier Tannier. A Benchmark Evaluation of Clinical Named Entity Recognition in French. In The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, Torino, Italy . [PDF]
• Rabab Alkhalifa, Hsuvas Borkakoty, Romain Deveaud, Alaa El-Ebshihy, Luis Espinosa-Anke, Tobias Fink, Gabriela Gonzalez-Saez, Petra Galuščáková, Lorraine Goeuriot, David Iommi, Maria Liakata, Harish Tayyar Madabushi, Pablo Medina-Alias, Philippe Mulhem, Florina Piroi, Martin Popel, Christophe Servan and Arkaitz Zubiaga LongEval: Longitudinal Evaluation of Model Performance at CLEF 2024. In Advances In Information Retrieval (ECIR 2024), Mar 2024, Glasgow (Ecosse), United Kingdom. pp.60-66, ⟨10.1007/978-3-031-56072-9_8⟩ . [PDF]
• Nadège Alavoine, Gaëlle Laperriere, Christophe Servan, Sahar Ghannay, Sophie Rosset New Semantic Task for the French Spoken Language Understanding MEDIA Benchmark. In The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024, Torino, Italy . [PDF]

2023

• Rabab Alkhalifa, Hsuvas Borkakoty, Romain Deveaud, Alaa El-Ebshihy, Luis Espinosa-Anke, Tobias Fink, Gabriela Gonzalez-Saez, Petra Galuščáková, Lorraine Goeuriot, David Iommi, Maria Liakata, Harish Tayyar Madabushi, Pablo Medina-Alias, Philippe Mulhem, Florina Piroi, Martin Popel, Christophe Servan and Arkaitz Zubiaga LongEval: Longitudinal Evaluation of Model Performance at CLEF 2023. In European Conference on Information Retrieval, Apr 2023, Dublin, Ireland. pp.499-505 . [PDF]
• Rabab Alkhalifa, Hsuvas Borkakoty, Romain Deveaud, Alaa El-Ebshihy, Luis Espinosa-Anke, Tobias Fink, Gabriela Gonzalez-Saez, Petra Galuščáková, Lorraine Goeuriot, David Iommi, Maria Liakata, Harish Tayyar Madabushi, Pablo Medina-Alias, Philippe Mulhem, Florina Piroi, Martin Popel, Christophe Servan and Arkaitz Zubiaga Overview of the CLEF-2023 LongEval Lab on Longitudinal Evaluation of Model Performance. In CLEF 2023: Experimental IR Meets Multilinguality, Multimodality, and Interaction, Sep 2023, Thessalonic, Greece. pp.440-458 . [PDF]

2022

• Oralie Cattan, Sahar Ghannay, Christophe Servan, Sophie Rosset Étude comparative de modèles Transformers en compréhension de la parole en français. In 34e Journées d'Etudes sur la Parole (JEP2022), Jun 2022, Île de Noirmoutier, France . [PDF]
• Oralie Cattan, Christophe Servan, Sophie Rosset On the Usability of Transformers-based models for a French Question-Answering task. In Joint Conference of the Information Retrieval Communities in Europe (CIRCLE) 2022, Jul 2022, Samatan, France . [PDF]
• Oralie Cattan, Sahar Ghannay, Christophe Servan, Sophie Rosset Benchmarking Transformers-based models on French Spoken Language Understanding tasks. In INTERSPEECH 2022, Sep 2022, Incheon, South Korea . [PDF]

2021

• Oralie cattan, Christophe Servan and Sophie Rosset. On the Usability of Transformers-based models for a French Question-Answering task. In Proceedings of Recent Advances in Natural Language Processing (RANLP2021), Varna, Bulgaria, September 2021. [PDF]
• Oralie cattan, Christophe Servan and Sophie Rosset. On the cross-lingual transferability of multilingual prototypical models accorss NLU tasks. In Proceedings of Meta Learning and Its Applications to Natural Language Processing, workshop at ACL 2021 (METANLP'2021), Bangkok, Thailand, August 2021. [PDF]

2020

• Sahar Ghannay, Christophe Servan and Sophie Rosset. Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation Task. In Proceedings of The 28th International Conference on Computational Linguistics (COLING'2020), Barcelona, Spain, December 2020. [PDF]
• Estelle Maudet and Christophe Servan. Conception d'un système de détection d'intention pour un moteur de recherche sur Internet. In The Proceedings of JEPs-TALN-RECITAL 2020, Nancy, France, July 2020.

2019

• Valentin Macé and Christophe Servan. Using Whole Document Context in Neural Machine Translation. In The Proceedings of 16th International Workshop on Spoken Language Translation 2019 (IWSLT2019), Hong Kong, China, November 2019. [PDF]
• Estelle Maudet, Oralie Cattan, Maureen De Seyssel, and Christophe Servan. Qwant Research @DEFT 2019: Document matching and information retrieval using clinical cases. In Atelier Défi Fouilles de Texte 2019, TOULOUSE, France, July 2019. [PDF]
• Maxime Portaz, Hicham Randrianarivo, Adrien Nivaggioli, Estelle Maudet, Christophe Servan, and Sylvain Peyronnet. Image search using multilingual texts: a cross-modal learning approach between image and text. In ArXiv, 2019. [PDF]
• Nasredine Semmar, Christophe Servan, Meriama Laib, Dhouha Bouamor, and Morgane Marchand. Extracting and Aligning Multiword Expressions from Parallel Corpora. Representation and parsing of multiword expressions, chapter 11. 2019.

2017

• Yongchao Deng, Jungi Kim, Guillaume Klein, Catherine KOBUS, Natalia Segal, Christophe Servan, Bo Wang, Dakun Zhang, Josep Crego, and Jean Senellart. SYSTRAN Purely Neural MT Engines for WMT2017. In Proceedings of the Second Conference on Machine Translation (WMT2017), Copenhagen, Denmark, September 2017.

2016

• Christophe Servan, Alexandre Bérard, Zied Elloumi, Hervé Blanchon, and Laurent Besacier. Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources?. In COLING 2016, Osaka, Japan, December 2016.
• Alexandre Bérard, Olivier Pietquin, Laurent Besacier, and Christophe Servan. Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation. In NIPS Workshop on end-to-end learning for speech and audio processing, Barcelona, Spain, December 2016.
• Jean Senellart, Christophe Servan, and Gaëlle Bou. Experience Pure Neural MT. White Paper, SYSTRAN, December 2016. Vulgarisation scientifique à destination des clients de SYSTRAN.
• Ngoc-Tien Le, Christophe Servan, Benjamin Lecouteux, and Laurent Besacier. Better Evaluation of ASR in Speech Translation Context Using Word Embeddings. In Interspeech 2016, San-Francisco, CA, USA, Septembre 2016.
• Christophe Servan, Zied Elloumi, Hervé Blanchon, and Laurent Besacier. Word2Vec vs DBnary ou comment (ré)concilier représentations distribuées et réseaux lexico-sémantiques ? Le cas de l’évaluation en traduction automatique. In La conférence conjointe JEP-TALN-RECITAL 2016, Juillet 2016.
• Alexandre Bérard, Christophe Servan, Olivier Pietquin, and Laurent Besacier. MultiVec: a multilingual and multilevel representation learning toolkit for NLP. In The 10th edition of the Language Resources and Evaluation Conference (LREC 2016), Mai 2016.
• Claude Roux and Christophe Servan. Sentence generation using linguistic information. Patent, 2016.
• Christophe Servan and Marc Dymetman. Terminological adaptation of statistical machine translation through automatic generation of phrasal contexts for bilingual terms. Patent, 2016.
• Josep Maria Crego, Jungi Kim, Guillaume Klein, Anabel Rebollo, Kathy Yang, Jean Senellart, Egor Akhanov, Patrice Brunelle, Aurelien Coquard, Yongchao Deng, Satoshi Enoue, Chiyo Geiss, Joshua Johanson, Ardas Khalsa, Raoum Khiari, Byeongil Ko, Catherine Kobus, Jean Lorieux, Leidiana Martins, Dang-Chuan Nguyen, Alexandra Priori, Thomas Riccardi, Natalia Segal, Christophe Servan, Cyril Tiquet, Bo Wang, Jin Yang, Dakun Zhang, Jing Zhou, and Peter Zoldan. SYSTRAN's Pure Neural Machine Translation Systems. Technical report, SYSTRAN, 2016.
• Christophe Servan, Josep Crego, and Jean Senellart. Domain specialization: a post-training domain adaptation for Neural Machine Translation. Technical report, SYSTRAN, 2016.

2015

• Christophe Servan and Marc Dymetman. Adaptation par enrichissement terminologique en traduction automatique statistique fondée sur la génération et le filtrage de bi-segments virtuels. In La 22ème Conférence sur le Traitement Automatique des Langues Naturelles, Caen, France, Juin 2015. ATALA.
• Christophe Servan, Ngoc-Tien Le, Ngoc Quang Luong, Benjamin Lecouteux, and Laurent Besacier. An Open Source Toolkit for Word-level Confidence Estimation in Machine Translation. In The 12th International Workshop on Spoken Language Translation (IWSLT'15), Da Nang, Vietnam, Décembre 2015.

2014

• Joern Wuebker, Hermann Ney, Martínez-Villaronga Adrià, Adrià Giménez, Alfons Juan, Christophe Servan, Marc Dymetman, and Shachar Mirkin. Comparison of Data Selection Techniques for the Translation of Video Lectures. In The eleventh biennial conference of the Association for Machine Translation in the Americas (AMTA-2014), Vancouver, Canada, Octobre 2014. AMTA.
• Mauro Cettolo, Nicola Bertoldi, Marcello Federico, Holger Schwenk, Loïc Barrault, and Christophe Servan. Translation project adaptation for MT-enhanced computer assisted translation. Machine Translation, 28:127, 2014.

2013

• Mauro Cettolo, Christophe Servan, Nicola Bertoldi, Marcello Federico, Loïc Barrault, and Holger Schwenk. Issues in Incremental Adaptation of Statistical MT from Human Post-edits. In MT Summit XIV Workshop on Post-editing Technology and Practice, Nice, France, Sep tembre 2013.

2012

• Christophe Servan, Patrik Lambert, Anthony Rousseau, Holger Schwenk, and Loïc Barrault. LIUM's SMT Machine Translation Systems for WMT 2012. In The Seventh Workshop on Statistical Machine Translation (WMT12), Montreal, Canada, Juin 2012.
• Christophe Servan and Simon Petitrenaud. Utilisation des fonctions de croyance pour l’estimation de paramètres en traduction automatique. In La conférence conjointe JEP-TALN-RECITAL 2012, Grenoble, France, Juin 2012.
• Christophe Servan and Simon Petitrenaud. Calculation of phrase probabilities for Statistical Machine Translation by using belief functions. In The 24th International Conference on Computational Linguistics (COLING 2012), Mumbai, India, Décembre 2012.

2011

• Nasredine Semmar, Christophe Servan, Dhouha Bouamor, and Ali Joua. Using Cross-Language Information Retrieval for Machine Translation. In Proceedings of the 5th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics, Poznań, Pologne, Novembre 2011.
• Patrik Lambert, Holger Schwenk, Christophe Servan, and Sadaf Abdul-Rauf. Investigations on Translation Model Adaptation Using Monolingual Data. In Sixth Workshop on Statistical Machine Translation, pages 284--293, Edinburgh, United Kingdom, Juillet 2011.
• Holger Schwenk, Patrik Lambert, Loïc Barrault, Christophe Servan, Haithem Afli, Sadaf Abdul-Rauf, and Kashif Shah. LIUM's SMT Machine Translation Systems for WMT 2011. In The Sixth workshop on Statistical Machine Translation, Edinburgh, United Kingdom, Juillet 2011.
• Christophe Servan and Holger Schwenk. Optimising Multiple Metrics with MERT. The Prague Bulletin of Mathematical Linguistics, (96):109, 2011.

2010

• Nasredine Semmar, Christophe Servan, Gaël De Chalendar, Benoît Le Ny, and Jean-Jacques Bouzaglou. A Hybrid Word Alignment Approach to Improve Translation Lexicons with Compound Words and Idiomatic Expressions. In The 32nd Translating and the Computer Conference - ASLIB, Londres, Royaume Uni, Novembre 2010.
• Christophe Servan, Nathalie Camelin, Christian Raymond, Frédéric Béchet, and Renato De Mori. On the Use of Machine Translation for Spoken Language Understanding Portability. In IEEE International Conference on Acoustics, Speech, and Signal Processing, pages 5330 -- 5333, Dallas, Texas, United States, Mars 2010. IEEE.
• Christophe Servan and Nasredine Semmar. A Hybrid Approach for Machine Translation Based on Cross-language Information Retrieval. In The International Workshop on Spoken Language Translation (IWSLT 2010), Paris, France, Décembre 2010.

2008

• Christophe Servan. Apprentissage automatique et compréhension dans le cadre d’un dialogue homme-machine téléphonique à initiative mixte. Phd Thesis, Avignon University, Décembre 2008.
• Frédéric Duvert, Marie-Jean Meurs, Christophe Servan, Frédéric Béchet, Fabrice Lefèvre, and Renato De Mori. Composition sémantique pour la compréhension de la parole dans un cadre de dialogue. In Les 27e Journées d’Etudes sur la Parole (JEP), Avignon, France, Juin 2008.
• Loïc Barrault, Christophe Servan, Driss Matrouf, Georges Linarès, and Renato De Mori. Frame-Based Acoustic Feature Integration for Speech Understanding. In IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008., 2008.
• Frédéric Duvert, Marie-Jean Meurs, Christophe Servan, Frédéric Béchet, Fabrice Lefèvre, and Renato De Mori. Semantic composition process in a speech understanding system. In The 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, United States, Mar s 2008.
• Christophe Servan and Frédéric Béchet. Fast call-classification system development without in-domain training data. In The proceedings of the International Conference on Speech and Language Processing (ICSLP) Interspeech 2008, Brisbane, Australia, Sep tembre 2008.

2006

• Christophe Servan. Utilisation des transducteurs dans le décodage conceptuel : application au corpus MEDIA. In MajecSTIC, Lorient, France, Novembre 2006.
• Christophe Servan, Christian Raymond, Frédéric Béchet, and Pascal Nocéra. Conceptual decoding from word lattices: application to the spoken dialogue corpus MEDIA. In The Ninth International Conference on Spoken Language Processing (Interspeech 2006 - ICSLP), Pittsburgh, United States, Septembre 2006.
• Christophe Servan, Christian Raymond, Frédéric Béchet, and Pascal Nocéra. Décodage conceptuel à partir de graphes de mots sur le corpus de dialogue Homme-Machine MEDIA. In Les XXVIes Journées d'Étude sur la Parole (JEP 2006), Dinard, France, Juin 2006.
• Hélène Bonneau-Maynard, Christelle Ayache, Frédéric Béchet, Alexandre Denis, Anne Kuhn, Fabrice Lefevre, Djamel Mostefa, Mathieu Quignard, Sophie Rosset, Christophe Servan, and Jeanne Villaneau. Results of the French Evalda-Media evaluation campaign for literal understanding. In The fifth international conference on Language Resources and Evaluation (LREC 2006), Genes, Italy, Mai 2006.
• Christophe Servan and Frédéric Béchet. Décodage conceptuel et apprentissage automatique : application au corpus de dialogue Homme-Machine MEDIA. In La 13ème édition de la conférence sur le Traitement Automatique des Langues Naturelles (TALN 2006), Louvain, Belgium, Avril 2006. Best paper Award.

Last updated on 2022-02-02