A Survey on paraphrase detection

• Main Authors: Yusdanis Feus P., Isvani Frías B.
• Format: Article
• Language: Spanish
• Published: Instituto Antioqueño de Investigación (IAI) 2015-12-01
• Series: Revista Antioqueña de las Ciencias Computacionales y la Ingeniería de Software (RACCIS)
• Subjects: Natural language processing; parapharase detection; similarity function; machine learning
• Online Access: http://fundacioniai.org//raccis/v5n2/n9a4.pdf

Paraphrase detection is commonly used in various research areas related to the natural language processing, as information extraction, machine translation, information retrieval and automatic identification of copyright infringement. Therefore, paraphrase detection has received a lot of attention in the last years. Methods for paraphrase detection aims at deciding whether or not two sentences have the same meaning. This paper reviews the main techniques and resources available for paraphrase detection. We focus our review on methods belonging to two different groups: 1) methods using a similarity function for paraphrase detection and 2) supervised algorithms relative to machine learning and data mining context.