1. End-to-end learning of LDA by mirror-descent back propagation over a deep architecture;chen;Proc Adv Neural Inf Process Syst,2015
2. Correlated topic models;blei;Proc Adv Neural Inf Process Syst,2006
3. Syntax aware LSTM model for Chinese semantic role labeling;qian;arXiv 1704 00405,2017
4. BERT: Pre-training of deep bidirectional transformers for language understanding;devlin;arXiv 1810 04805,2018