- XLNet is a state-of-the-art neural network designed for various NLP tasks.
- Researchers from Carnegie Mellon University and Google released a new pre-trained language model called XLNet
- The previous state-of-the-art language model is BERT, which achieves a GLUE (General Language Understanding Evaluation) score of 80.5%. GLUE is a benchmark for training, evaluating, and analyzing natural language understanding systems, and the human baseline score is 87.1%.
- pytorch transformer is used which is developed by huggingface.
1. (https://ai.googleblog.com/2017/08/transformer-novel-neural-network.html)
2. (https://towardsdatascience.com/bert-classifier-just-another-pytorch-model-881b3cf05784)
3. (https://blog.essen.ai/what-is-xlnet-and-how-does-it-work/)