Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection

Neural language models such as BERT allow for human-like text paraphrasing. This ability threatens academic integrity, as it aggravates identifying machine-obfuscated plagiarism. We make two contributions to foster the research on detecting these novel machine-paraphrases. First, we provide the firs...

Full description

Bibliographic Details

Published in:	2021 ACM/IEEE Joint Conference on Digital Libraries (JCDL) pp. 226 - 229
Main Authors:	Wahle, Jan Philip, Ruas, Terry, Meuschke, Norman, Gipp, Bela
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.09.2021
Subjects:	Benchmark testing BERT Bit error rate Codes Encyclopedias Paraphrase detection Plagiarism Semantics Transformers
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!