Paper
Overcoming the Curse of Sentence Length for Neural Machine Translation\n using Automatic Segmentation
The authors of (Cho et al., 2014a) have shown that the recently introduced\nneural network translation systems suffer from a significant drop in\ntranslation quality when translating long sentences, unlike existing\nphrase-based translation systems. In this paper, we propose a way to address\nthis issue by automatically segmenting an input sentence into phrases that can\nbe easily translated by the neural network translation model. Once each segment\nhas been independently translated by the neural machine translation model, the\ntranslated clauses are concatenated to form a final translation. Empirical\nresults show a significant improvement in translation quality for long\nsentences.\n
Authors: Pouget-Abadie, Jean · Bahdanau, Dzmitry · van Merrienboer, Bart · Cho, Kyunghyun · Bengio, Yoshua