Hint-based Training for Non-Autoregressive Translation

By Zhuohan Li, Di He, Fei Tian, Tao Qin, Liwei Wang, Tie-Yan Liu. 2018

21 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Di He
5. Jiatao Gu
6. Junliang Guo
7. Kyunghyun Cho
8. Furu Wei

Citations in the corpus

• MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices (2020, background): “Li et al. (2019) proposed to transfer the similarity of hidden states and word alignment from an autoregressive Transformer teacher to a non-autoregressive student.”
• Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input (2018, background): “Therefore, the three kinds of attentions along with residual connections (He et al. 2016) and layer normalization (Ba, Kiros, and Hinton 2016) constitute our model.”
• Fully Non-autoregressive Neural Machine Translation: Tricks of the Trade (2020, background): “…advantage, fully NAT system – model makes parallel predictions with single neural network forward – still lags behind in translation quality and has not been fully explored in literature (Libovick´y and Helcl, 2018; Li et al., 2018; Sun et al., 2019; Ma et al., 2019; Ghazvininejad et al., 2020a).”