Korean-English Machine Translation with Multiple Tokenization Strategy
This work addresses tokenization optimization for Korean-English translation, but it is incremental as it compares existing methods without introducing new techniques.
The study investigated how different tokenization methods affect Korean-English machine translation performance, finding that using BPE for Korean and morpheme tokenization for English achieved the best BLEU score of 35.73.
This work was conducted to find out how tokenization methods affect the training results of machine translation models. In this work, alphabet tokenization, morpheme tokenization, and BPE tokenization were applied to Korean as the source language and English as the target language respectively, and the comparison experiment was conducted by repeating 50,000 epochs of each 9 models using the Transformer neural network. As a result of measuring the BLEU scores of the experimental models, the model that applied BPE tokenization to Korean and morpheme tokenization to English recorded 35.73, showing the best performance.