Research on Applicability of Sentence Similarity Algorithms in Text Copy Detection

摘要

Sentence similarity computation is the research topic of domain of natural language processing, and plays an important role in the example-based machine translation, information retrieval, text mining and other fields. Those sentence similarity algorithms have different applicability in different environments. This paper reviewed and analyzed five kinds of sentence similarity algorithm, and tested them in the field of text copy detection. In the end, the effect of different sentence similarity algorithms to the result of text copy detection was analyzed and evaluated.