Short bio
Diplôme d’Ingénieur (ENSTA Paris)
Master 2 MVA (ENS Paris-Saclay)
Thesis title
Contextual Machine Translation of User Generated Contents.
Short abstract
Machine Translation has seen huge progress in the last years, mainly thanks to deep learning. However, machine translation systems dramatically fail to translate noisy texts generated by users (containing grammar and syntax errors, emojis, jargon…) and to handle contextual information. We aim to investigate the cases of failure and to build systems both robust to noise and able to leverage various contextual sources to translate ambiguous sentences correctly.