%0 Generic %1 pouget2014 %A Pouget-Abadie, Jean %A Bahdanau, Dzmitry %A van Merrienboer, Bart %A Cho, Kyunghyun %A Bengio, Yoshua %D 2014 %K encoder-decoder rnn uw_ws17_ml %T Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation %U http://arxiv.org/abs/1409.1257 %X 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.

@misc{pouget2014, abstract = {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.}, added-at = {2017-11-19T10:50:57.000+0100}, author = {Pouget-Abadie, Jean and Bahdanau, Dzmitry and van Merrienboer, Bart and Cho, Kyunghyun and Bengio, Yoshua}, biburl = {https://www.bibsonomy.org/bibtex/2f33f9c1d31dfb4dc26320dbc86e3247b/izzy278}, interhash = {c39470ac2b6808319d394f14bc780db9}, intrahash = {f33f9c1d31dfb4dc26320dbc86e3247b}, keywords = {encoder-decoder rnn uw_ws17_ml}, note = {cite arxiv:1409.1257Comment: Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8)}, timestamp = {2017-11-19T10:50:57.000+0100}, title = {Overcoming the Curse of Sentence Length for Neural Machine Translation using Automatic Segmentation}, url = {http://arxiv.org/abs/1409.1257}, year = 2014 }