Detecting short passages of similar text in large document collections

@misc{citeulike:2937480, abstract = {This paper presents a statistical method for fingerprinting text. In a large collection of independently written documents each text is associated with a fingerprint which should be di\#erent from all the others. If fingerprints are too close then it is suspected that passages of copied or similar text occur in two documents. Our method exploits the characteristic distribution of word trigrams, and measures to determine similarity are based on set theoretic principles. The system was developed...}, author = {Lyon, C. and Malcolm, J. and Dickerson, B. }, citeulike-article-id = {2937480}, keywords = {intertextuality, pair\_project, plagiarism, similarity}, posted-at = {2008-06-27 15:58:24}, priority = {2}, title = {Detecting short passages of similar text in large document collections}, url = {http://citeseer.ist.psu.edu/lyon01detecting.html}, year = {2001} }

TY - GEN ID - citeulike:2937480 L3 - citeulike-article-id:2937480 TI - Detecting short passages of similar text in large document collections N2 - This paper presents a statistical method for fingerprinting text. In a large collection of independently written documents each text is associated with a fingerprint which should be di#erent from all the others. If fingerprints are too close then it is suspected that passages of copied or similar text occur in two documents. Our method exploits the characteristic distribution of word trigrams, and measures to determine similarity are based on set theoretic principles. The system was developed... KW - intertextuality KW - pair_project KW - plagiarism KW - similarity AU - Lyon, C AU - Malcolm, J AU - Dickerson, B PY - 2001/// UR - http://citeseer.ist.psu.edu/lyon01detecting.html ER -