WikiTransfer: Knowledge transfer from High-Resource to Low-Resource Language in Multilingual Wikipedia

Paramita Das, Amartya Roy, Animesh Mukherjee

To address content disparities in multilingual Wikipedia versions, in this work, we propose a lightweight framework called WikiTransfer that can help enhance knowledge integrity across diverse linguistic communities. The framework employs powerful machine translation techniques to translate text from highresource to low-resource language for transferring information. Our proposed framework aims to improve overall content quality, demonstrated through its effectiveness in enhancing the quality of Wikipedia articles at the section level. Although We have shown a case study of knowledge transfer from English to Hindi, WikiTransfer can be adapted to transfer potential knowledge across various language pairs.