Semantically-informed distance and similarity measures for paraphrase plagiarism identification

[EN] 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 simila...

Descripción completa

Detalles Bibliográficos
Autores: Álvarez Carmona, M.A., Franco-Salvador, Marc, Villatoro-Tello, Esaú, Montes Gomez, Manuel, Villaseñor Pineda, Luis, Rosso, Paolo
Tipo de recurso: artículo
Fecha de publicación:2018
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/146280
Acceso en línea:https://riunet.upv.es/handle/10251/146280
Access Level:acceso abierto
Palabra clave:Plagiarism identification
Paraphrase plagiarism
Semantic similarity
Edit distance
Word2vec representation
LENGUAJES Y SISTEMAS INFORMATICOS
Descripción
Sumario:[EN] 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.