Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation
This addresses a key bottleneck for neural machine translation systems, improving performance on long sentences, though it is an incremental method.
The paper tackled the problem of neural machine translation quality dropping for long sentences by proposing automatic segmentation into phrases, which are translated independently and concatenated, resulting in significant improvement in translation quality for long sentences.
The authors of (Cho et al., 2014a) have shown that the recently introduced neural network translation systems suffer from a significant drop in translation quality when translating long sentences, unlike existing phrase-based translation systems. In this paper, we propose a way to address this issue by automatically segmenting an input sentence into phrases that can be easily translated by the neural network translation model. Once each segment has been independently translated by the neural machine translation model, the translated clauses are concatenated to form a final translation. Empirical results show a significant improvement in translation quality for long sentences.