The DEFT challenge is a French text mining evaluation workshop. The 2011 edition will focus on diachronic variation within French press corpora, and matches between a scientific article with his abstract. The closing workshop will be held during the TALN2011 conference in Montpellier (34).
For this new edition, we propose two distinct tasks: diachronic variation on press corpora and matches between scientific articles and abstract.
Teams participating to DEFT2011 will have to register using the online form and sign the end user agreement. Training corpora will be made available to registered teams from February 21st. These corpora are composed from 60% of original corpora. The remaining 40% of corpora will be used for the test. The test will take place during from April 4th. Starting from a chosen date within this period, participants benefit from three days to apply on the test corpora the methods developed on the training corpora.