1. Conditional random fields: Probabilistic models for segmenting and labeling sequence data;lafferty;Proc 18th Int Conf Mach Learn,2001
2. Long Short-Term Memory
3. Bidirectional LSTM-CRF models for sequence tagging;huang;arXiv 1508 01991,2015
4. Attention is all you need;vaswani;arXiv 1706 03762,2017
5. Adam: A method for stochastic optimization;kingma;arXiv 1412 6980,2014