top of page


alice and eve no year.png

Franciska de Jong


Author Nellie McClung once claimed that “people must know the past to understand the present and face the future”. Knowing the past, though, might result a complex endeavour. Take, for instance, the rebuilding of Balkan states after the Yugoslav Wars. It has been mentioned that, to succeed in doing so, the articulation of war experiences among its great variety of citizens - from Croatians to North-Macedonians - is a necessary condition. How to do this, though? How can the voices of such a variety of citizens, all having had different experiences during that war, be collected and made comprehensible to all? Not to forget, of course, that they all speak different languages.

The articulation of these ‘Balkan Voices’ is exactly what language technologist Franciska de Jong intents to do with a project going by the same name. To do so, she embarks on creating ‘language models’, which are statistical representations of spoken words and their underlying connections. Eventually, using speech recognition technologies, those language models must ensure the oral history of the Yugoslav Wars to become a written one. As already mentioned, this is a complex task as the former Yugoslavia knows a great variety of languages. Nevertheless, the year of 2014 saw Franciska and her research colleagues presenting its first results: a collection of 400 interviews recorded in Croatia for the documentation of personal war- related experiences.

The way Franciska uses Computer Science and Language and Literature to complement each other stems from a time long before the ‘Balkan Voices’-project was initiated. After her PhD in Language Theory, she did pioneering work in the area of automated machine translation at Philips Research in 1985 - at that time a tough problem that seemed impossible to solve. After that, she has become Full Professor of Language Technology at the University of Twente in 1992 and, as of 2015, she has equally become Full Professor of e-Research for the Humanities at the University of Utrecht. Her current research interest is in line with the course of such a career: creating access technologies for digital libraries, text mining, cross-language retrieval and the disclosure of cultural heritage collections. Evidently, ‘Balkan Voices’ is a great example of the latter. Moreover, being the executive director of CLARIN ERIC, Franciska devotes herself to providing scholars in the Humanities and Social Sciences access to digital language data and processing tools all across Europe.

Indeed, Franciska has contributed greatly - and still is - to the ‘marriage’ of the Humanities and Computer Science. She seems to be a spiritual heir of Ada Lovelace, who equally pondered that such a combination could enable opportunities for collaborative creativity. As Franciska herself once steadily claimed, she will not abide by the belief that people can only possess ‘alfa’ or ‘beta’ qualities. She possesses both.

Franciska de Jong


See all videos about 

Franciska de Jong

About them

About their work

Sorry, no video available

Sorry, no video available


See all images related to 

Franciska de Jong

bottom of page