My main research interest is how to support underserved language communities in the Wikiworld. The first step in this direction was investigating language distributions in the content of Wikidata, published at OpenSym as A Glimpse into Babel: An Analysis of Multilinguality in Wikidata.
I am very involved with the ArticlePlaceholder extension. It aims to bring together Wikidata's multilingual information and missing content on underserved Wikipedias. It is currently deployed on 14 Wikipedias, and can be seen for example on the Creole Wikipedia.
I published two papers with the goal of extending the ArticlePlaceholder in small language communities with generated text. Mind the (Language) Gap: Generation of Multilingual Wikipedia Summaries from Wikidata for ArticlePlaceholders and Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata.
|Users by language|