UM4: unified multilingual multiple teacher-student model for zero-resource neural machine translation

J Yang, Y Yin, S Ma, D Zhang, S Wu, H Guo… - arxiv preprint arxiv …, 2022 - arxiv.org
Most translation tasks among languages belong to the zero-resource translation problem
where parallel corpora are unavailable. Multilingual neural machine translation (MNMT) …

Prompt refinement with image pivot for text-to-image generation

J Zhan, Q Ai, Y Liu, Y Pan, T Yao, J Mao, S Ma… - arxiv preprint arxiv …, 2024 - arxiv.org
For text-to-image generation, automatically refining user-provided natural language prompts
into the keyword-enriched prompts favored by systems is essential for the user experience …

Improving statistical machine translation for a resource-poor language using related resource-rich languages

P Nakov, HT Ng - Journal of Artificial Intelligence Research, 2012 - jair.org
We propose a novel language-independent approach for improving machine translation for
resource-poor languages by exploiting their similarity to resource-rich ones. More precisely …

Investigations on translation model adaptation using monolingual data

P Lambert, H Schwenk, C Servan… - Sixth Workshop on …, 2011 - hal.science
Most of the freely available parallel data to train the translation model of a statistical machine
translation system comes from very specific sources (European parliament, United Nations …