Egon works on the creation, standardisation, and interoperability of tools for editing, processing, and annotating linguistic data. He collects and processes data from the Web, from social media, and language learners and also enjoys working together with other scientists on their data. He develops tools that can apply our everyday understanding of language to texts, be it to help teachers to correct texts, students to write texts or just interested people who search for content in texts that elude a simple Google search. His curiosity in research is driven by the question of why people can easily find meaning in texts, even at a young age, while automatic processes are often of little use or fail completely.

He is an advocate of open science to make research and data available for others to consult or reuse in new research, and he is the leader of this CLARIN K-centre for CMC.