Abstract
Recent research on multilingual statistical machine translation (SMT) focuses on the usage of pivot languages in order to overcome resource limitations for certain language pairs. This paper proposes a new method to translate a dialect language into a foreign language by integrating transliteration approaches based on Bayesian alignment (BA) models with pivot-based SMT approaches. The advantages of the proposed method with respect to standard SMT approaches are threefold: (1) it uses a standard language as the pivot language and acquires knowledge about the relation between dialects and a standard language automatically, (2) it avoids segmentation mismatches between the input and the translation model by mapping the character sequences of the dialect language to the word segmentation of the standard language, and (3) it reduces the translation task complexity by using monotone decoding techniques. Experiment results translating five Japanese dialects (Kumamoto, Kyoto, Nagoya, Okinawa, Osaka) into four Indo-European languages (English, German, Russian, Hindi) and two Asian languages (Chinese, Korean) revealed that the proposed method improves the translation quality of dialect translation tasks and outperforms standard pivot translation approaches concatenating SMT engines for the majority of the investigated language pairs.
