1.Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension 2.Commonsense for Generative Multi-Hop Question Answering Tasks 3.Dynamic Integration of Background Knowledge in Neural NLU Systems 4.Explicit Utilization of General Knowledge in Machine Reading Comprehension 5.Knowledgeable Reader_ Enhancing Cloze-Style Reading Comprehension with External Commonsense Kg 6.simple and effective text matching. with richer alignment features 7.Enhanced LSTM for Natural Language Inference 8.EDA