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 …
X Garcia, O Firat - arXiv preprint arXiv:2202.11822, 2022 - arxiv.org
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 …