Phát hiện sao chép văn bản liên ngữ trong tài liệu tiếng việt

• Tác giả: Quang Hùng Lê, Thị Anh Thi Nguyễn
• Ngôn ngữ: vie
• Ký hiệu phân loại: 495.92 Languages of East and Southeast Asia Sino-Tibetan languages
• Thông tin xuất bản: Khoa học, 2013
• Mô tả vật lý: 79-87
• Bộ sưu tập: Metadata
• ID: 559530

Tóm tắt

Along with the development of the Internet, text copying or "plagiarism" is becoming a serious problem nowadays. Some researchers have proposed different methods of detecting text copying in Vietnamese documents. However, these methods are only effective in monolingual texts. This paper presents a new method of automatic cross-language text copying detection relying on n-gram. Several experiments conducted on English and Vietnamese texts have showed significant results.