Language-Agnostic detection of Current Events across Wikipedia

Abstract

Currently, English Wikipedia alone includes over 6,660,000 articles and it averages 550 new articles per day. To assist the readers in identifying pages that cover recent noteworthy occurrences the Current Events portal was implemented. However, this portal is maintained manually with notable quality differences across languages. The main goal of this work is to establish the task of supervised event detection in Wikipedia and propose a language-agnostic solution to address this problem. This is an important milestone towards improving the quality of the Current Events Portal for the languages with not many active editor communities. In this work, we reviewed existing research on this topic, and by combining and enriching those existing solutions, we proposed a current event detection dataset based on the Current Events Portal updates and Wikipedia pages’ features. Also, we developed a language-agnostic event detection model and reported its performance in English, German, and Polish languages, showing that is possible to automatize this task. The outcome of this work can be used to assist Wikipedia editors to keep the Current Event portal updated, saving time and the human effort used on this task.