Future-Prediction-Based Model for Neural Machine Translation
We propose a novel model for Neural Machine Translation (NMT). Different from the conventional method, our model can predict the future text length and words at each decoding time step so that the generation can be helped with the information from the future prediction. With such information, the model does not stop generation without having translated enough content. Experimental results demonstrate that our model can significantly outperform the baseline models. Besides, our analysis reflects that our model is effective in the prediction of the length and words of the untranslated content.
Code (0)
등록된 구현이 없습니다.
Tasks
Future predictionMachine TranslationNMTPredictionTranslationSimilar Papers 제목 키워드 기반
Dual Past and Future for Neural Machine Translation
Though remarkable successes have been achieved by Neural Machine Translation (NMT) in recent years, it still suffers from the inadequate-translation problem. Previous studies show that explicitly modeling the Past and Fu…
Machine TranslationNMTSentenceTranslationPrediction Improves Simultaneous Neural Machine Translation
Simultaneous speech translation aims to maintain translation quality while minimizing the delay between reading input and incrementally producing the output. We propose a new general-purpose prediction action which predi…
Machine TranslationPredictionreinforcement-learningReinforcement Learning+2Modeling Future for Neural Machine Translation by Fusing Target Information
Sequence-to-sequence Neural Machine Translation (NMT) models have achieved excellent performance. However, the NMT decoder only makes predictions based on the source and the target historical context, ignores the target …
DecoderMachine TranslationNMTTranslationModeling Fluency and Faithfulness for Diverse Neural Machine Translation
Neural machine translation models usually adopt the teacher forcing strategy for training which requires the predicted sequence matches ground truth word by word and forces the probability of each prediction to approach …
Machine TranslationPredictionTranslationIntroducing Mouse Actions into Interactive-Predictive Neural Machine Translation
The quality of the translations generated by Machine Translation (MT) systems has highly improved through the years and but we are still far away to obtain fully automatic high-quality translations. To generate them and …
Machine TranslationTranslation