@InProceedings{vanderwees-bisazza-monz:2016:WNUT, author = {van der Wees, Marlies and Bisazza, Arianna and Monz, Christof}, title = {A Simple but Effective Approach to Improve Arabizi-to-English Statistical Machine Translation}, booktitle = {Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)}, month = {December}, year = {2016}, address = {Osaka, Japan}, publisher = {The COLING 2016 Organizing Committee}, pages = {43--50}, abstract = {A major challenge for statistical machine translation (SMT) of Arabic-to-English user-generated text is the prevalence of text written in Arabizi, or Romanized Arabic. When facing such texts, a translation system trained on conventional Arabic-English data will suffer from extremely low model coverage. In addition, Arabizi is not regulated by any official standardization and therefore highly ambiguous, which prevents rule-based approaches from achieving good translation results. In this paper, we improve Arabizi-to-English machine translation by presenting a simple but effective Arabizi-to-Arabic transliteration pipeline that does not require knowledge by experts or native Arabic speakers. We incorporate this pipeline into a phrase-based SMT system, and show that translation quality after automatically transliterating Arabizi to Arabic yields results that are comparable to those achieved after human transliteration.}, url = {http://aclweb.org/anthology/W16-3908} }