Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau et al., 2015, Neural Machine Translation by Jointly Learning to Align and Translate (3rd International Conference on Learning Representations (ICLR 2015))
Subscriber deck — free during early access
1 cards in “5.2.2 Long Sentences” · whole deck
5.2.2 Long Sentences
- Why does RNNsearch translate long sentences better than RNNencdec?It needn’t encode a whole long sentence perfectly into a fixed vector, only the parts around each word accurately. In examples, RNNencdec-50 drifted from the meaning after about 30 words (e.g. “based on his status as a health care worker” became “based on his state of health”), while RNNsearch-50 kept all details.
- Bahdanau et al., 2015, Neural Machine Translation by Jointly Learning to Align and Translate (3rd International Conference on Learning Representations (ICLR 2015)), §5.2.2
Source
- Dzmitry Bahdanau, Kyunghyun Cho and Yoshua Bengio. 2015. Neural Machine Translation by Jointly Learning to Align and Translate. In 3rd International Conference on Learning Representations (ICLR 2015). https://arxiv.org/abs/1409.0473