Monolingually Derived Phrase Scores for Phrase Based SMT Using Neural Networks Vector Representations
This work addresses a bottleneck in machine translation by enhancing parameter estimation with monolingual data, though it is incremental as it builds on existing neural representation models.
The paper tackled the problem of estimating phrase-based machine translation parameters from monolingual data by proposing two new features based on neural network vector representations, recovering over 80% of BLEU loss from removed phrase table probabilities and improving BLEU score by 0.74 points.
In this paper, we propose two new features for estimating phrase-based machine translation parameters from mainly monolingual data. Our method is based on two recently introduced neural network vector representation models for words and sentences. It is the first time that these models have been used in an end to end phrase-based machine translation system. Scores obtained from our method can recover more than 80% of BLEU loss caused by removing phrase table probabilities. We also show that our features combined with the phrase table probabilities improve the BLEU score by absolute 0.74 points.