Improving the Performance of Neural Machine Translation Involving Morphologically Rich Languages
This addresses translation challenges for morphologically rich languages, offering incremental improvements in performance and attention mechanism efficacy.
The paper tackled the problem of neural machine translation for morphologically rich languages like Tamil, showing that using Word2Vec embeddings improved BLEU scores by 0.73 points over a baseline, and morphological segmentation further boosted performance by 7.05 BLEU points while reducing vocabulary size by a factor of 8.
The advent of the attention mechanism in neural machine translation models has improved the performance of machine translation systems by enabling selective lookup into the source sentence. In this paper, the efficiencies of translation using bidirectional encoder attention decoder models were studied with respect to translation involving morphologically rich languages. The English - Tamil language pair was selected for this analysis. First, the use of Word2Vec embedding for both the English and Tamil words improved the translation results by 0.73 BLEU points over the baseline RNNSearch model with 4.84 BLEU score. The use of morphological segmentation before word vectorization to split the morphologically rich Tamil words into their respective morphemes before the translation, caused a reduction in the target vocabulary size by a factor of 8. Also, this model (RNNMorph) improved the performance of neural machine translation by 7.05 BLEU points over the RNNSearch model used over the same corpus. Since the BLEU evaluation of the RNNMorph model might be unreliable due to an increase in the number of matching tokens per sentence, the performances of the translations were also compared by means of human evaluation metrics of adequacy, fluency and relative ranking. Further, the use of morphological segmentation also improved the efficacy of the attention mechanism.