Affiliations: [a] Department of Computer Science, Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE), Mexico
| [b]
Symanto Research, Nuremberg, Germany
| [c] PRHLT Research Center, Universitat Politècnica de València, Spain
| [d] Department of Information Technologies, Language and Reasoning Research Group, Universidad Autónoma Metropolitana, Unidad Cuajimalpa (UAM-C), Mexico
Correspondence:
[*]
Corresponding author. Miguel A. Álvarez-Carmona, Department of Computer Science, Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE), Mexico. E-mail: [email protected].
Abstract: Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the relatedness of two given texts: a semantically-informed similarity measure and a semantically-informed edit distance. Both measures are able to extract semantic information from either an external resource or a distributed representation of words, resulting in informative features for training a supervised classifier for detecting paraphrase plagiarism. Obtained results indicate that the proposed metrics are consistently good in detecting different types of paraphrase plagiarism. In addition, results are very competitive against state-of-the art methods having the advantage of representing a much more simple but equally effective solution.
