User Pic

Fethi Bougares

/ Associate professor

LST ( Le Mans )

(+33) 02 43 83 38 47


Research Activities:



Corpus : Multi30k, TSAC



I am an associate professor in the Computer Science Department at Le Mans University. I am also part of the Language and Speech technology (LST) team at the LIUM Laboratory.  My Ph.D is from Le Mans University where I worked in the field of Automatic Speech Recognition. I hold a Master degree’s in Computer Science from Grenoble University UGF and INPG. I also have a bachelor’s degree in Computer Science from the university of Monastir, Tunisia. My professional interests include Speech Recognition, Machine Transaltion and Arabic Natural Language Processing. I am also interested in the application of deep learning methods to low resource languages.

HAL Publications  Hal[authIdHal_s][]=fethi-bougares

LIUM Publications - 42

[1]Ha Nguyen, Fethi Bougares, Natalia Tomashenko, Yannick Estève, Laurent Besacier. Investigating Self-supervised Pre-training for End-to-end Speech Translation. Interspeech 2020, Oct 2020, Shangai (Virtual Conf), China. <hal-02962186>
[2]Maha Elbayad, Ha Nguyen, Fethi Bougares, Natalia Tomashenko, Antoine Caubrière, et al.. ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020. Proceedings of the 17th International Conference on Spoken Language Translation, Jul 2020, Seattle, WA, United States. pp.35-43, ⟨10.18653/v1/2020.iwslt-1.2⟩. <hal-02895893>
[3]Mercedes Garcia-Martinez, Loïc Barrault, Fethi Bougares. Addressing Data Sparsity for Neural Machine Translation Between Morphologically Rich Languages. Machine Translation, Springer Verlag, 2020. <hal-02505563>
[4]Manh Ha Nguyen, Natalia Tomashenko, Marcely Zanon Boito, Antoine Caubrière, Fethi Bougares, et al.. ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task. 16th International Workshop on Spoken Language Translation 2019, Nov 2019, Hong Kong, China. <hal-02352949>
[5]Adrien Bardet, Fethi Bougares, Loïc Barrault. A Study on Multilingual Transfer Learning in Neural Machine Translation: Finding the Balance Between Languages. Statistical Language and Speech Processing (SLSP 2019), Oct 2019, Ljubljana, Slovenia. pp.59-70, ⟨10.1007/978-3-030-31372-2_5⟩. <hal-02435899>
[6]Saméh Kchaou, Fethi Bougares, Lamia Hadrich-Belguith. LIUM-MIRACL Participation in the MADAR Arabic Dialect Identification Shared Task. Proceedings of the Fourth Arabic Natural Language Processing Workshop, Aug 2019, Florence, France. pp.219-223, ⟨10.18653/v1/W19-4625⟩. <hal-02435895>
[7]Fethi Bougares, Jane Wottawa, Anne Baillot, Loïc Barrault, Adrien Bardet. LIUM’s Contributions to the WMT2019 News Translation Task: Data and Systems for German-French Language Pairs. Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), Aug 2019, Florence, France. pp.129-133, ⟨10.18653/v1/W19-5307⟩. <hal-02405788>
[8]Loïc Barrault, Fethi Bougares, Lucia Specia, Chiraag Lala, Desmond Elliott, et al.. Findings of the Third Shared Task on Multimodal Machine Translation. THIRD CONFERENCE ON MACHINE TRANSLATION (WMT18), Oct 2018, Brussels, Belgium. pp.308 - 327, ⟨10.18653/v1/W18-6402⟩. <hal-02008843>
[9]Ozan Caglayan, Adrien Bardet, Fethi Bougares, Loïc Barrault, Kai Wang, et al.. LIUM-CVC Submissions for WMT18 Multimodal Translation Task. Third Conference on Machine Translation, Oct 2018, Brussels, Belgium. pp.597 - 602, ⟨10.18653/v1/W18-64065⟩. <hal-02498133>
[10]Abir Masmoudi, Fethi Bougares, Mariem Ellouze, Yannick Estève, Lamia Belguith. Automatic speech recognition system for Tunisian dialect . Language Resources and Evaluation, Springer Verlag, 2018, 52 (1), pp.249-267. ⟨10.1007/s10579-017-9402-y⟩. <hal-01592416>
[11]Mercedes Garcia-Martinez, Loïc Barrault, Fethi Bougares. Neural Machine Translation by Generating Multiple Linguistic Factors. 5th International Conference Statistical Language and Speech Processing SLSP 2017, Oct 2017, Le Mans, France. ⟨10.1007/978-3-319-68456-7_2⟩. <hal-01689270>
[12]Franck Burlot, Mercedes Garcia-Martinez, Loïc Barrault, Fethi Bougares, François Yvon. Word Representations in Factored Neural Machine Translation. Conference on Machine Translation, Association for Computational Linguistics, Sep 2017, Copenhagen, Denmark. pp.43 - 55. <hal-01618384>
[13]Salima Mdhaffar, Fethi Bougares, Yannick Estève, Lamia Hadrich-Belguith. Sentiment Analysis of Tunisian Dialects: Linguistic Ressources and Experiments. Third Arabic Natural Language Processing Workshop (WANLP), Apr 2017, Valence, Spain. pp.55-61, ⟨10.18653/v1/W17-1307⟩. <hal-01592418>
[14]Caglar Gulcehre, O. Firat, Kelvin Xu, Kyunghyun Cho, Loïc Barrault, et al.. On using monolingual corpora in neural machine translation. 2017. <hal-01454942>
[15]Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes Garcia-Martinez, Fethi Bougares, et al.. LIUM-CVC Submissions for WMT17 Multimodal Translation Task. SECOND CONFERENCE ON MACHINE TRANSLATION, 2017, Copenhagen, Denmark. pp.432 - 439. <hal-01742382>
[16]Ozan Caglayan, Mercedes Garcia-Martinez, Adrien Bardet, Walid Aransa, Fethi Bougares, et al.. NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems. The Prague Bulletin of Mathematical Linguistics, Univerzita Karlova v Praze, 2017, 109 (1), ⟨10.1515/pralin-2017-0035⟩. <hal-01647873>
[17]Mercedes Garcia-Martinez, Ozan Caglayan, Walid Aransa, Adrien Bardet, Fethi Bougares, et al.. LIUM Machine Translation Systems for WMT17 News Translation Task. Second Conference on Machine Translation, 2017, Copenhagen, Denmark. pp.288 - 295. <hal-01742378>
[18]Ozan Caglayan, Walid Aransa, Yaxing Wang, Marc Masana, Mercedes Garcia-Martinez, et al.. Does Multimodality Help Human and Machine for Translation and Image Captioning?. First Conference on Machine Translation, Aug 2016, Berlin, Germany. pp.627-633. <hal-01433183>
[19]Mercedes Garcia-Martinez, Loïc Barrault, Fethi Bougares. Factored Neural Machine Translation Architectures. International Workshop on Spoken Language Translation (IWSLT'16), 2016, Seattle, United States. <hal-01433161>
[20]Kashif Shah, Fethi Bougares, Loïc Barrault, Lucia Specia. SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features. First Conference on Machine Translation, 2016, Berlin, Germany. <hal-01433190>
[21]Abir Masmoudi, Mariem Ellouze, Fethi Bougares, Yannick Estève, Lamia Hadrich-Belguith. Conditional Random Fields for the Tunisian Dialect Grapheme-to-Phoneme Conversion. Interspeech 2016, 2016, San Francisco (CA, USA), Unknown Region. <hal-01433177>
[22]Alex Ter-Sarkisov, Holger Schwenk, Loïc Barrault, Fethi Bougares. Incremental Adaptation Strategies for Neural Network Language Models. 3rd Workshop on Continuous Vector Space Models and their Compositionality (CVSC), 2015, Beijing, China. pp.48--56. <hal-01454943>
[23]Frédéric Blain, Fethi Bougares, Amir Hazem, Loïc Barrault, Holger Schwenk. Continuous Adaptation to User Feedback for Statistical Machine Translation. North American Chapter of the Association for Computational Linguistics – Human Language Technologies (NAACL HLT 2015), 2015, Denver (Colorado, USA), Unknown Region. <hal-01454944>
[24]Fethi Bougares, Houda Bouamor. UMMU@ QALB-2015 Shared Task: Character and Word level SMT pipeline for Automatic Error Correction of Arabic Text. Arabic Natural Language Processing Workshop, 2015, Doha, Qatar. <hal-01433204>
[25]Frédéric Blain, Amir Hazem, Fethi Bougares, Loïc Barrault, Holger Schwenk. Project Adaptation for SMT Over Several Days. Translation in Transition conference, 2015, Germersheim, Germany. <hal-01433211>
[26]Holger Schwenk, Fethi Bougares, Loïc Barrault. Efficient training strategies for deep neural network language models.. NIPS workshop on deep neural networks and representation learning, 2014, Montreal, Canada. <hal-01454946>
[27]Fethi Bougares, Anthony Rousseau, Paul Deléglise, Yannick Estève, Loïc Barrault, et al.. Développement et évaluation d’un système de traduction automatique de la parole en Pashto vers le Français. JEP 2014, 2014, Le Mans, France. <hal-01433217>
[28]Kyunghyun Cho, Bart Merrienboer, Caglar Gulcehre, Fethi Bougares, Holger Schwenk, et al.. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. EMNLP, 2014, Unknown, Unknown Region. <hal-01433235>
[29]Abir Masmoudi, Yannick Estève, Mariem Ellouze Khmekhem, Fethi Bougares, Lamia Hadrich Belguith. Phonetic tool for the Tunisian Arabic. SLTU'2014, The 4th International Workshop on spoken Language Technologies for Under-resourced Languages, 2014, Saint-Petersburg, Russia. <hal-01433236>
[30]Abir Masmoudi, Mariem Ellouze Khemakhem, Yannick Estève, Fethi Bougares, Lamia Hadrich Belguith, et al.. Phonétisation automatique du dialecte tunisien. JEP 2014, 2014, Le Mans, France. <hal-01433231>
[31]Fethi Bougares, Paul Deléglise, Yannick Estève, Mickael Rouvier. LIUM ASR system for ETAPE French evaluation campaign: experiments on system combination using open-source recognizers. Sixteenth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2013), 2013, Pilsen, Czech Republic. <hal-01450691>
[32]Fethi Bougares, Mickael Rouvier, Nathalie Camelin, Paul Deléglise, Yannick Estève. An investigation of single-pass ASR system combination for Spoken Language Understanding. 1st International Conference on Statistical Language and Speech Processing (SLSP 2013), 2013, Tarragona, Spain. <hal-01433263>
[33]Fethi Bougares. Attelage de systèmes de transcription automatique de la parole. Ordinateur et société [cs.CY]. Université du Maine, 2012. Français. ⟨NNT : 2012LEMA1026⟩. <tel-00839990>
[34]Fethi Bougares, Mickael Rouvier, Yannick Estève, Georges Linarès. Low latency combination of parallelized single-pass LVCSR systems. Interspeech, Sep 2012, Portland, United States. <hal-01313238>
[35]Fethi Bougares, Yannick Estève, Paul Deléglise, Mickael Rouvier, Georges Linarès. Avancées dans le domaine de la transcription automatique par décodage guidé. JEP, 2012, Grenoble, France. <hal-01433463>
[36]Fethi Bougares, Yannick Estève, Paul Deléglise, Georges Linarès. Bag of n-gram driven decoding for LVCSR system harnessing. Automatic speech recognition and Understanding Workshop, 2011, Hawaï (USA), Unknown Region. <hal-01434931>
[37]Anthony Rousseau, Fethi Bougares, Paul Deléglise, Holger Schwenk, Yannick Estève. LIUM’s systems for the IWSLT 2011 Speech Translation Tasks. International Workshop on Spoken Language Translation, 2011, San Francisco (USA), Unknown Region. <hal-01454949>
[38]Fethi Bougares. Amélioration de la combinaison de systèmes de reconnaissance de la parole par décodage guide. Rencontre de Jeune Chercheur en Parole, 2011, Grenoble, France. <hal-01433511>
[39]Richard Dufour, Fethi Bougares, Yannick Estève, Paul Deléglise. Unsupervised model adaptation on targeted speech segments for LVCSR system combination. Interspeech 2010, 2010, Makuhari, Japan. <hal-01433900>
[40]Yannick Estève, Paul Deléglise, Sylvain Meignier, Simon Petitrenaud, Holger Schwenk, et al.. Some recent research work at LIUM based on the use of CMU Sphinx. CMU SPUD Workshop, 2010, Dallas (Texas), Unknown Region. <hal-01434933>
[41]Fethi Bougares, Laurent Besacier, Hervé Blanchon. LIG approach for IWSLT09 : Using Multiple Morphological Segmenters for Spoken Language Translation of Arabic. International Workshop on Spoken Language Translation, 2009, Tokyo, Unknown Region. <hal-01455704>
[42]Fethi Bougares. Traduction automatique de la parole arabe/anglais par segmentations multiples. RJCP, 2009, Avignon, France. <hal-01433946>