jpelhaw/xlnet-base-plagiarism-detection

This is the checkpoint for LMGC based on XLNet-base after being trained on the Machine-Paraphrased Plagiarism Dataset:  - The xlnet-base model page . The model can be loaded with a tokenizer like so: autoModelForSequenceClassification, AutoTokenizer.from_pretrained. (autoregressive) The model has been trained to perform the detection of plagiarism in the past . It is based on a model that can be used to train LMGC-based models . The XlNet-LMGC-M is a generalized Autoregressive Pretraining for Language Understanding. The model is trained on,