Faster decoding for subword level Phrase-based SMT between related languages
This work addresses decoding efficiency for machine translation between related languages, but it is incremental as it optimizes existing methods rather than introducing new paradigms.
The paper tackled the problem of increased decoding time in subword-level phrase-based statistical machine translation between related languages by investigating decoder parameters and data formats, resulting in suggested settings that significantly improve decoding speed with minimal impact on translation accuracy.
A common and effective way to train translation systems between related languages is to consider sub-word level basic units. However, this increases the length of the sentences resulting in increased decoding time. The increase in length is also impacted by the specific choice of data format for representing the sentences as subwords. In a phrase-based SMT framework, we investigate different choices of decoder parameters as well as data format and their impact on decoding time and translation accuracy. We suggest best options for these settings that significantly improve decoding time with little impact on the translation accuracy.