Papers with supervised MT
Flow-Adapter Architecture for Unsupervised Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | Recent advances in deep learning have boosted the development of neural machine translation (NMT). |
| Approach: | They propose a flow-adapter architecture for unsupervised neural machine translation that leverages normalizing flows to model distributions of sentence-level latent representations. |
| Outcome: | The proposed model achieves competitive results on several unsupervised MT benchmarks. |
Unsupervised Paraphrasing without Translation (P19-1)
Copied to clipboard
| Challenge: | Recent work on automatic paraphrasing focuses on methods leveraging machine translation as an intermediate step. |
| Approach: | They propose to learn paraphrasing models only from a monolingual corpus . they propose a residual variant of vector-quantized variational auto-encoder . |
| Outcome: | The proposed model outperforms supervised and unsupervised translation methods in paraphrase identification and training set augmentation. |