no code implementations • IWSLT 2016 • Mercedes García-Martínez, Loïc Barrault, Fethi Bougares
A qualitative analysis of the output on a set of test sentences shows the effectiveness of the FNMT model.
no code implementations • WMT (EMNLP) 2020 • Loïc Barrault, Magdalena Biesialska, Marta R. Costa-jussà, Fethi Bougares, Olivier Galibert
A lifelong learning system can adapt to new data without forgetting previously acquired knowledge.
no code implementations • 11 Dec 2022 • Fethi Bougares, Salim Jouili
Speech translation (ST) is the task of directly translating acoustic speech signals in a source language into text in a foreign language.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
no code implementations • IWSLT (ACL) 2022 • Marcely Zanon Boito, John Ortega, Hugo Riguidel, Antoine Laurent, Loïc Barrault, Fethi Bougares, Firas Chaabani, Ha Nguyen, Florentin Barbier, Souhir Gahbiche, Yannick Estève
This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and dialect speech translation.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • LREC 2022 • Marcely Zanon Boito, Fethi Bougares, Florentin Barbier, Souhir Gahbiche, Loïc Barrault, Mickael Rouvier, Yannick Estève
In this paper we present two datasets for Tamasheq, a developing language mainly spoken in Mali and Niger.
no code implementations • WS 2020 • Maha Elbayad, Ha Nguyen, Fethi Bougares, Natalia Tomashenko, Antoine Caubrière, Benjamin Lecouteux, Yannick Estève, Laurent Besacier
This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, offline speech translation and simultaneous speech translation.
no code implementations • LREC 2020 • Najla Ben Abdallah, Sam{\'e}h Kchaou, Fethi Bougares
We use the term {'}sub-dialect{'} to refer to the dialects belonging to the same country.
no code implementations • EMNLP (IWSLT) 2019 • Ha Nguyen, Natalia Tomashenko, Marcely Zanon Boito, Antoine Caubriere, Fethi Bougares, Mickael Rouvier, Laurent Besacier, Yannick Esteve
This paper describes the ON-TRAC Consortium translation systems developed for the end-to-end model task of IWSLT Evaluation 2019 for the English-to-Portuguese language pair.
no code implementations • WS 2019 • Fethi Bougares, Jane Wottawa, Anne Baillot, Lo{\"\i}c Barrault, Adrien Bardet
This paper describes the neural machine translation (NMT) systems of the LIUM Laboratory developed for the French↔German news translation task of the Fourth Conference onMachine Translation (WMT 2019).
no code implementations • WS 2019 • Sam{\'e}h Kchaou, Fethi Bougares, Lamia Hadrich-Belguith
This paper describes the joint participation of the LIUM and MIRACL Laboratories at the Arabic dialect identification challenge of the MADAR Shared Task (Bouamor et al., 2019) conducted during the Fourth Arabic Natural Language Processing Workshop (WANLP 2019).
no code implementations • JEPTALNRECITAL 2019 • Adrien Bardet, Fethi Bougares, Lo{\"\i}c Barrault
L{'}apprentissage par transfert est une solution au probl{\`e}me de l{'}apprentissage de syst{\`e}mes de traduction automatique neuronaux pour des paires de langues peu dot{\'e}es.
1 code implementation • WS 2018 • Lo{\"\i}c Barrault, Fethi Bougares, Lucia Specia, Chiraag Lala, Desmond Elliott, Stella Frank
In this task a source sentence in English is supplemented by an image and participating systems are required to generate a translation for such a sentence into German, French or Czech.
no code implementations • WS 2018 • Ozan Caglayan, Adrien Bardet, Fethi Bougares, Loïc Barrault, Kai Wang, Marc Masana, Luis Herranz, Joost Van de Weijer
This paper describes the multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT18 Shared Task on Multimodal Translation.
no code implementations • 5 Dec 2017 • Mercedes García-Martínez, Loïc Barrault, Fethi Bougares
FNMT system is designed to manage larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size).
no code implementations • WS 2017 • Desmond Elliott, Stella Frank, Loïc Barrault, Fethi Bougares, Lucia Specia
The multilingual image description task was changed such that at test time, only the image is given.
no code implementations • WS 2017 • Ozan Caglayan, Walid Aransa, Adrien Bardet, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Marc Masana, Luis Herranz, Joost Van de Weijer
This paper describes the monomodal and multimodal Neural Machine Translation systems developed by LIUM and CVC for WMT17 Shared Task on Multimodal Translation.
1 code implementation • WS 2017 • Mercedes García-Martínez, Ozan Caglayan, Walid Aransa, Adrien Bardet, Fethi Bougares, Loïc Barrault
This paper describes LIUM submissions to WMT17 News Translation Task for English-German, English-Turkish, English-Czech and English-Latvian language pairs.
1 code implementation • 1 Jun 2017 • Ozan Caglayan, Mercedes García-Martínez, Adrien Bardet, Walid Aransa, Fethi Bougares, Loïc Barrault
nmtpy has been used for LIUM's top-ranked submissions to WMT Multimodal Machine Translation and News Translation tasks in 2016 and 2017.
1 code implementation • WS 2017 • Salima Medhaffar, Fethi Bougares, Yannick Est{\`e}ve, Lamia Hadrich-Belguith
There are many existing researches in the field of Arabic language Sentiment Analysis (SA); however, they are generally restricted to Modern Standard Arabic (MSA) or some dialects of economic or political interest.
1 code implementation • 15 Sep 2016 • Mercedes García-Martínez, Loïc Barrault, Fethi Bougares
In addition, we can produce new words that are not in the vocabulary.
1 code implementation • 13 Sep 2016 • Ozan Caglayan, Loïc Barrault, Fethi Bougares
We show that a dedicated attention for each modality achieves up to 1. 6 points in BLEU and METEOR compared to a textual NMT baseline.
1 code implementation • WS 2016 • Ozan Caglayan, Walid Aransa, Yaxing Wang, Marc Masana, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Joost Van de Weijer
This paper presents the systems developed by LIUM and CVC for the WMT16 Multimodal Machine Translation challenge.
no code implementations • 11 Mar 2015 • Caglar Gulcehre, Orhan Firat, Kelvin Xu, Kyunghyun Cho, Loic Barrault, Huei-Chi Lin, Fethi Bougares, Holger Schwenk, Yoshua Bengio
Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation.
no code implementations • WS 2015 • Aram Ter-Sarkisov, Holger Schwenk, Loic Barrault, Fethi Bougares
We present efficient techniques to adapt a neural network language model to new data.
43 code implementations • 3 Jun 2014 • Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN).
Ranked #47 on Machine Translation on WMT2014 English-French