Postdoc Computational Linguistics and Text Mining (0,8 fte)
Online discussions contain a wealth of information, but are notoriously difficult to read. Finding a piece of information in an online discussion is arguably even harder, certainly when reading it on a mobile device, as is more and more common. The NWO DiscoSumo project studies how online discussions can be automatically summarised, so that they can be read easier, on mobile devices and elsewhere. As a result, the threshold for mobile users to participate in online discussions will be significantly lowered, and the general quality and understanding of these discussions may be expected to increase.
The project is a collaboration between computational linguists and text mining researchers at Tilburg University (Sander Wubben, Emiel Krahmer) and Radboud University (Florian Kunneman, Antal van den Bosch). The data is provided by Sanoma Media BV., one of the largest publishers in The Netherlands, who also participates in the project. More information can be found here: http://discosumo.ruhosting.nl/
To strengthen our team, we are looking for a computational linguist, with experience in text mining, information extraction and/or automatic summarisation. You will help with the development and evaluation of a system that is capable of summarising on line discussion threads. In addition, you will contribute 0.2 fte to the teaching program of Communication and Information Sciences (CIS), teaching a course and supervising students.
This job comes from a partnership with Science Magazine and