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
2 cards in “5.1 Quantitative Results” · whole deck
5.1 Quantitative Results
- How did RNNsearch compare with RNNencdec and Moses in BLEU?RNNsearch beat RNNencdec in all settings: on all test sentences 26.75 vs 17.82 (trained on ≤50 words), and RNNsearch-30 even beat RNNencdec-50. On sentences without unknown words, RNNsearch-50 trained longer scored 36.15, above Moses (35.63), which also used a 418M-word monolingual corpus.
model all no UNK RNNencdec-30 13.93 24.19 RNNsearch-30 21.50 31.44 RNNencdec-50 17.82 26.71 RNNsearch-50 26.75 34.16 RNNsearch-50, trained longer 28.45 36.15 Moses 33.30 35.63 - Bahdanau et al., 2015, Neural Machine Translation by Jointly Learning to Align and Translate (3rd International Conference on Learning Representations (ICLR 2015)), §5.1
- How did translation quality depend on sentence length?RNNencdec’s BLEU dropped dramatically as sentences got longer, while RNNsearch was much more robust; RNNsearch-50 showed no deterioration even for sentences of 50 or more words.
- Bahdanau et al., 2015, Neural Machine Translation by Jointly Learning to Align and Translate (3rd International Conference on Learning Representations (ICLR 2015)), §5.1
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