Conference article

Comparison between NMT and PBSMT Performance for Translating Noisy User-Generated Content

José Carlos Rosales Nuñez
Université Paris Sud, LIMSI, France / Université Paris Saclay, France / INRIA Paris, France

Djamé Seddah
INRIA Paris, France

Guillaume Wisniewski
Université Paris Sud, LIMSI, France / Université Paris Saclay, Franc

Download article

Published in: Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland

Linköping Electronic Conference Proceedings 167:1, p. 2--14

NEALT Proceedings Series 42:1, p. 2--14

Show more +

Published: 2019-10-02

ISBN: 978-91-7929-995-8

ISSN: 1650-3686 (print), 1650-3740 (online)


This work compares the performances achieved by Phrase-Based Statistical Machine Translation systems (PB- SMT) and attention-based Neuronal Machine Translation 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 expected, PBSMT outperforms NMT when translating non-canonical inputs. Our error analysis uncovers the speci- ficities of UGC that are problematic for sequential NMT architectures and suggests new avenue for improving NMT models.


Machine Translation User Generated Content Neural Machine Translation PBSMT


No references available

Citations in Crossref