Simple Automatic Post-editing for Arabic-Japanese Machine Translation
This work addresses the bottleneck of lacking parallel data for low-resource language pairs like Arabic-Japanese, offering a domain-specific solution that is incremental in nature.
The paper tackled the problem of machine translation for the low-resource Arabic-Japanese language pair by adapting a state-of-the-art neural MT system using a simple automatic post-editing technique on a unique parallel corpus of Arabic news articles translated to Japanese, resulting in a viable approach for specific domains.
A common bottleneck for developing machine translation (MT) systems for some language pairs is the lack of direct parallel translation data sets, in general and in certain domains. Alternative solutions such as zero-shot models or pivoting techniques are successful in getting a strong baseline, but are often below the more supported language-pair systems. In this paper, we focus on Arabic-Japanese machine translation, a less studied language pair; and we work with a unique parallel corpus of Arabic news articles that were manually translated to Japanese. We use this parallel corpus to adapt a state-of-the-art domain/genre agnostic neural MT system via a simple automatic post-editing technique. Our results and detailed analysis suggest that this approach is quite viable for less supported language pairs in specific domains.