This work compares the performances achieved by Phrase-Based Statistical Ma- chine Translation systems (PBSMT) and attention-based Neural Machine Transla- tion systems (NMT) when translating User Generated Content (UGC), as encountered in social medias, from French to English. We show that, contrary to what could be ex- pected, PBSMT outperforms NMT when translating non-canonical inputs. Our error analysis uncovers the specificities of UGC that are problematic for sequential NMT architectures and suggests new avenue for improving NMT models.