Dr Loïc Barrault
PhD
Department of Computer Science
Senior Lecturer
Director of Research Computing
Member of the Natural Language Processing (NLP) research group
- Profile
-
Loïc Barrault (M) is a Senior Lecturer in the Natural Language Processing group at the University of Sheffield. He obtained his PhD at the University of Avignon in 2008 in the field of automatic speech recognition. He then did 2 years as researcher and 9 years as Associate Professor at LIUM, Le Mans Université working on statistical and neural machine translation.
Loïc Barrault participated in many international projects, namely EuroMatrix+, MateCAT, DARPA BOLT, and national projects, namely ANR Cosmat, “Projet d’Investissement d’Avenir” PACTE and a large industrial project PEA TRAD. He coordinated the EU ChistERA M2CR project and is currently actively involved in the ChistERA ALLIES project.
- Research interests
-
Loïc's research work focuses on statistical and neural machine translation, by including linguistics aspects (factored neural machine translation), by considering multiple modalities (multimodal neural machine translation) and by designing lifelong learning methods for MT. He is one of the organisers of the Multimodal Machine Translation shared task at WMT.
- Publications
-
Books
- A general framework toweight heterogeneous parallel data for model adaptation in statistical machine translation.
Journal articles
- Addressing data sparsity for neural machine translation between morphologically rich languages. Machine Translation. View this article in WRRO
- Introduction to the special issue on deep learning approaches for machine translation. Computer Speech & Language, 46, 367-373.
- NMTPY: A Flexible Toolkit for Advanced Neural Machine Translation Systems. Prague Bulletin of Mathematical Linguistics, Special Issue on Open Source Tools for Machine Translation.
- Building and using multimodal comparable corpora for machine translation. Natural Language Engineering, 22(4), 603-625.
- Translation project adaptation for MT-enhanced computer assisted translation. Machine Translation, 28(2), 127-150.
- MANY: Open Source Machine Translation System Combination. Prague Bulletin of Mathematical Linguistics, Special Issue on Open Source Tools for Machine Translation, 145-155.
Chapters
- Parallel Texts Extraction from Multimodal Comparable Corpora, Advances in Natural Language Processing (pp. 40-51).
Conference proceedings papers
- Findings of the 2019 Conference on Machine Translation (WMT19). Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1) (pp 1-61)
- Probing the Need for Visual Context in Multimodal Machine Translation. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) (pp 4159-4170). Minneapolis, Minnesota, 2 June 2019 - 7 June 2019. View this article in WRRO
- MULTIMODAL GROUNDING FOR SEQUENCE-TO-SEQUENCE SPEECH RECOGNITION. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) (pp 8648-8652)
- A Study on Multilingual Transfer Learning in Neural Machine Translation: Finding the Balance Between Languages (pp 59-70)
- CAT tools in DH training. Proceedings of the 2019 Digital Humanities Conference
- Übersetzung als Bestandteil eines philologischen B.A.-Curriculums mit DH-Schwerpunkt. DHd 2019 - 6. Jahrestagung des Verbands Digital Humanities im deutschsprachigen Raum
- A Workflow For On The Fly Normalisation Of 17th c. French. Proceedings of the 2019 Digital Humanities Conference
- How2: A Large-scale Dataset for Multimodal Language Understanding. Proceedings of the Workshop on Visually Grounded Interaction and Language (NeurIPS 2018)
- LIUM-CVC Submissions for WMT18 Multimodal Translation Task. Proceedings of the Third Conference on Machine Translation, Volume 2. Shared Task Papers (pp 603-608)
- What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), Vol. 1 (pp 2126-2136)
- Findings of the Third Shared Task on Multimodal Machine Translation. Proceedings of Third Conference on Machine Translation
- Supervised Learning of Universal Sentence Representations from Natural Language Inference Data. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (pp 670-680). Copenhagen, Denmark, 9 September 2017 - 11 September 2017.
- Very deep convolutional networks for text classification. Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, Vol. 1 (pp 1107-1116). Valencia, Spain, 3 April 2017 - 7 April 2017. View this article in WRRO
- LIUM Machine Translation Systems for WMT17 News Translation Task. Second Conference on Machine Translation
- Word Representations in Factored Neural Machine Translation. Proceedings of the Second Conference on Machine Translation, September 2017 - September 2017.
- LIUM-CVC Submissions for WMT17 Multimodal Translation Task. Second Conference on Machine Translation
- Supervised Learning of Universal Sentence Representations from
Natural Language Inference Data. Proceedings of the 2017 Conference on Empirical Methods in Natural
Language Processing, September 2017 - September 2017. View this article in WRRO
- Neural Machine Translation by Generating Multiple Linguistic Factors (pp 21-31)
- SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features. First Conference on Machine Translation
- Does Multimodality Help Human and Machine for Translation and Image Captioning?. First Conference on Machine Translation
- Factored Neural Machine Translation Architectures.. International Workshop on Spoken Language Translation (IWSLT’16)
- OCR Error Correction Using Statistical Machine Translation. 16th International Conference on Intelligent Text Processing and Computational Linguistics (CICLing 2015).
- The LIUM ASR and SLT Systems for IWSLT 2015. 12th International Workshop on Spoken Language Translation (IWSLT 2015)
- Improving Continuous Space Language Models using Auxiliary Features. International Workshop on Spoken Language Translation (IWSLT’15)
- Incremental Adaptation Strategies for Neural Network Language Models.. 3rd Workshop on Continuous Vector Space Models and their Compositionality (CVSC) (pp 48-56)
- Continuous adaptation to user feedback for statistical machine translation. NAACL HLT 2015 - 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp 1001-1005)
- Efficient training strategies for deep neural network language models.. NIPS workshop on deep neural networks and representation learning
- The LIUM English-to-French Spoken Language Translation System and the Vecsys/LIUM Automatic Speech Recognition System for Italian Language for IWSLT 2014. International Workshop on Spoken Language Translation (IWSLT)
- Using Hypothesis Selection Based Features for Confusion Network MT System Combination. Third Workshop on Hybrid Approaches to Translation (HyTra), EACL 2014
- Développement et évaluation d’un système de traduction automatique de la parole en Pashto vers le Français. Actes de la conférence JEP 2014
- Multimodal Comparable Corpora for Machine Translation. 7th Workshop on Building and Using Comparable Corpora, Building Resources for Machine Translation Research
- The MateCat Tool
- Issues in Incremental Adaptation of Statistical MT from Human Post-edits. Proc. of the MT Summit XIV Workshop on Post-editing Technology and Practice (WPTP-2)
- Parallel Texts Extraction from Multimodal Comparable Corpora (pp 40-51)
- LIUM”s SMT Machine Translation Systems for WMT 2012. Proceedings of the Seventh Workshop on Statistical Machine Translation (pp 369-373)
- Semi-supervised Transliteration Mining from Parallel and Comparable Corpora. IWSLT
- Machine Translation System Combination with MANY for ML4HMT. Shared Task on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT (ML4HMT-2011)
- LIUM”s SMT Machine Translation Systems for WMT 2011. Proceedings of the 6th Workshop on Statistical Machine Translation
- Parametric Weighting of Parallel Data for Statistical Machine Translation. The 5th International Joint Conference on Natural Language Processing
- Some recent research work at LIUM based on the use of CMU Sphinx. CMU SPUD Workshop
- Translation Model Adaptation by Resampling. WMT, Association of Computational Linguistics (ACL) (pp in press-in press)
- SMT and SPE Machine Translation Systems for WMT”09. Fourth ACL Workshop on Statistical Machine Translation (WMT”09) (pp 130-134)
- LIUM”s Statistical Machine Translation Systems for IWSLT 2009. International Workshop on Spoken Language Translation (IWSLT’09) (pp 65-70)
- Frame-based acoustic feature integration for speech understanding. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, 31 March 2008 - 4 April 2008.
- Combinaison de differents jeux de paramètres acoustiques pour la reconnaissance automatique de la parole. Journées d’Études sur la Parole (JEP’08)
- Characterizing feature variability in automatic speech recognition systems. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Vol. 5
- Dynamic selection of acoustic features in an automatic speech recognition system. European Signal Processing Conference
- A General Method for Combining Acoustic Features in an Automatic Speech Recognition System. ITRW on Speech Recognition and Intrinsic Variation
- Variability of automatic speech recognition systems using different features. 9th European Conference on Speech Communication and Technology (pp 221-224)
- Étude des Variabilités de Systèmes de Reconnaissance Automatique de la Parole Utilisant des Paramètres Acoustiques Différents. Rencontres des Jeunes Chercheurs en Parole (RJCP’05)
- LIUM”s Statistical Machine Translation System for IWSLT 2010. International Workshop on Spoken Language Translation (IWSLT) 2010
- MANY: Open Source MT System Combination at WMT’10. ACL Workshop on Statistical Machine Translation (WMT’10)
- MANY improvements for WMT”11. Proceedings of the 6th Workshop on Statistical Machine Translation (pp 135-139)
- Multimodal Comparable Corpora as Resources for Extracting Parallel Data: Parallel Phrases Extraction. International Joint Conference on Natural Language Processing
- Traduction automatique à partir de corpus comparables: extraction de phrases parallèles à partir de données comparables multimodales. TALN
- Findings of the Second Shared Task on Multimodal Machine Translation and
Multilingual Image Description. Proceedings of the Second Conference on Machine Translation, 2017,
pp. 215--233
Presentations
- Project Adaptation for SMT Over Several Days.
- A general framework toweight heterogeneous parallel data for model adaptation in statistical machine translation.