The TALP-UPC System for the WMT Similar Language Task: Statistical vs Neural Machine Translation
It addresses translation challenges for similar language pairs, but the results are incremental as they compare existing methods without introducing new techniques.
The paper compared statistical and neural machine translation for similar languages, finding that statistical methods outperformed neural by 6 BLEU points for Spanish-Portuguese, while neural surpassed statistical by 2 BLEU points for Czech-Polish, with the TALP-UPC system achieving top rankings in a WMT task.
Although the problem of similar language translation has been an area of research interest for many years, yet it is still far from being solved. In this paper, we study the performance of two popular approaches: statistical and neural. We conclude that both methods yield similar results; however, the performance varies depending on the language pair. While the statistical approach outperforms the neural one by a difference of 6 BLEU points for the Spanish-Portuguese language pair, the proposed neural model surpasses the statistical one by a difference of 2 BLEU points for Czech-Polish. In the former case, the language similarity (based on perplexity) is much higher than in the latter case. Additionally, we report negative results for the system combination with back-translation. Our TALP-UPC system submission won 1st place for Czech-to-Polish and 2nd place for Spanish-to-Portuguese in the official evaluation of the 1st WMT Similar Language Translation task.