The article is devoted to a review of approaches to solving the problem of identifying paraphrases. This problem's relevance and use in tasks such as plagiarism detection, text simplification, and information search are described. Several classes of solutions were considered. The first approach is based on manual rules - it uses manually selected features based on the fundamental properties of paraphrases. The second approach is based on lexical similarity and various databases and ontologies. Machine learning-based approaches are also presented in this paper and describe different architectures that can be used to identify paraphrases. The last approach considered is based on deep learning and modern models of transformers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.