||Plagiarism is a current problem in many scientific and cultural fields.1
It is not uncommon to find documents that have not been originally
written (be partially or completely) by their claimed authors. These
cases of plagiarism
arise from the facility of electronically accessing texts written by
other people as well as retrieving documents directly from Internet Web
In the seminar I will present the state-of-the-art of plagiarism detection
with reference (when a suspicious document is compared to a set of potential
source documents), intrinsic plagiarism (when stylometric and other text
inherent features are considered in order to detect fragments of the
suspicious document that could be plagiarised) as well as cross-lnaguage
plagiarism (when a text fragment in one language is plagiarised from a
text in another language).
Last, I will describe how the 2nd competition on plagiarism detection
will be organised as a Lab at CLEF-2010 under the sponsorship of Yahoo!