Plagiarism detection in Punjabi Documents

Plagiarism is un-authorized use of the original work done by someone else and presenting as one¿s own work, without giving any acknowledgements to the original author. The evil of plagiarism has been around since the human beings started documenting their work. Plagiarism in the literary and research articles has always been a discouraging factor for the genuine authors and researchers. The special tools for plagiarism detection on the other end came as a big relief to the researchers. These specialized software tools are available in the market as proprietary, commercial solutions or even in the open source form. Many such tools work efficiently with English language documents, but fail to give satisfactory results for the documents written in linguistically complex languages like Hindi, Punjabi and other regional languages of India. The tool discussed in this text combines the ease of PHP, robustness of MySQL and a blend of Natural Language Processing techniques (NLP) for detecting plagiarism in Punjabi text documents.