Text Generation aims to produce plausible and readable text in human language from input
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …

Neural Machine Translation (NMT) has seen tremendous growth in the last ten years since
the early 2000s and has already entered a mature phase. While considered the most widely …

In this work, we investigate a more realistic unsupervised multimodal machine translation
(UMMT) setup, inference-time image-free UMMT, where the model is trained with source-text …

We consider the problem of multilingual unsupervised machine translation, translating to
and from languages that only have monolingual data by using auxiliary parallel language …

We explore the use of natural language prompts for controlling various aspects of the
outputs generated by machine translation models. We demonstrate that natural language …

The scarcity of parallel data is a major obstacle for training high-quality machine translation
systems for low-resource languages. Fortunately, some low-resource languages are …

Unsupervised translation has reached impressive performance on resource-rich language
pairs such as English-French and English-German. However, early studies have shown that …

We present a probabilistic framework for multilingual neural machine translation that
encompasses supervised and unsupervised setups, focusing on unsupervised translation …

In this paper, we introduced our joint team SJTU-NICT's participation in the WMT 2020
machine translation shared task. In this shared task, we participated in four translation …

For most language combinations, parallel data is either scarce or simply unavailable. To
address this, unsupervised machine translation (UMT) exploits large amounts of …