On the effective transfer of knowledge from English to Hindi Wikipedia

The work accepted at COLING (Industry Track) 2025 is contributed by Paramita Das, Amartya Roya, Ritabrata Chakraborty and Animesh Mukherjee.

Overview

There exists a significant disparity in the quality of content between high-resource languages (HRLs, e.g., English) and low-resource languages (LRLs, e.g., Hindi) versions of Wikipedia articles, with many LRL articles lacking adequate knowledge. To bridge these content gaps, we propose a framework to enhance knowledge equity between English and Hindi. In case the English Wikipedia page is not up-to-date, our framework extracts relevant information from external resources readily available (such as English books) and adapts it to align with Wikipedia’s distinctive style, including its neutral point of view (NPOV) policy, using in-context learning capabilities of large language models. The adapted content is then machine-translated into Hindi for integration into the corresponding Hindi Wikipedia articles. On the other hand, if the English version is comprehensive and up-to-date, the framework directly transfers knowledge from English to Hindi.