Recent impressive improvements in NLP, largely based on the success of contextual neural
language models, have been mostly demonstrated on at most a couple dozen high-resource …

Sentiment classification has been crucial for many natural language processing (NLP)
applications, such as the analysis of movie reviews, tweets, or customer feedback. A …

Phrase-based statistical machine translation (PB-SMT) has been the dominant paradigm in
machine translation (MT) research for more than two decades. Deep neural MT models have …

RoCS-MT, a Robust Challenge Set for Machine Translation (MT), is designed to test MT
systems' ability to translate user-generated content (UGC) that displays non-standard …

This paper describes LIMSI's submissions to the translation shared tasks at WMT'20. This
year we have focused our efforts on the biomedical translation task, developing a resource …

This work takes a critical look at the evaluation of user-generated content automatic
translation, the well-known specificities of which raise many challenges for MT. Our analyses …

Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT)
research for more than two decades, but has since been superseded by neural MT (NMT) …

This paper investigates effects of noisy source texts (containing spelling and grammar
errors, informal words or expressions, etc.) on human and machine translations, namely …

We present an approach to correct noisy User Generated Content (UGC) in French aiming to
produce a pretreatement pipeline to improve Machine Translation for this kind of non …

This work presents a novel Variational Neural Machine Translation (VNMT) architecture with
enhanced robustness properties, which we investigate through a detailed case-study …