We discuss how references and citations within a document to particular sources can be verified and guaranteed. When a document refers through a quotation to another document, th...
This paper presents a language identification technique that detects Latin-based languages of imaged documents without OCR. The proposed technique detects languages through the wo...
This paper presents a lightweight method for unsupervised extraction of paraphrases from arbitrary textual Web documents. The method differs from previous approaches to paraphrase...