Bi-Text Alignment of Movie Subtitles for Spoken English-Arabic Statistical Machine Translation
This work addresses the need for better resources in spoken language translation, specifically for English-Arabic, though it is incremental as it builds on existing subtitle-based methods.
The paper tackled the problem of aligning movie subtitle fragments for English-Arabic machine translation by developing an original algorithm that uses time information, resulting in a two BLEU point absolute improvement when added to training data.
We describe efforts towards getting better resources for English-Arabic machine translation of spoken text. In particular, we look at movie subtitles as a unique, rich resource, as subtitles in one language often get translated into other languages. Movie subtitles are not new as a resource and have been explored in previous research; however, here we create a much larger bi-text (the biggest to date), and we further generate better quality alignment for it. Given the subtitles for the same movie in different languages, a key problem is how to align them at the fragment level. Typically, this is done using length-based alignment, but for movie subtitles, there is also time information. Here we exploit this information to develop an original algorithm that outperforms the current best subtitle alignment tool, subalign. The evaluation results show that adding our bi-text to the IWSLT training bi-text yields an improvement of over two BLEU points absolute.