A Survey on Paraphrase Recognition

Paraphrase Recognition is a task of growing interest in the natural language process (NLP) research during the last years. This task aims to detect if two sentences have the same meaning. Paraphrase relationship described in this work is not the definition given by the common knowledge, but is more natural language oriented since it is driven by a lot of background human knowledge. This type of relation can be used as a support for many other NLP applications, such as Question Answering, Multi-document Summarization and for Machine Translation too. This paper presents an overview of the different phenomena that lead to paraphrase, of the methods used for Paraphrase Recognition and of different data-sets used for the task evaluation and of the main issue still opened.