PhD Dissertation Defense by Sicheng Yu | Mitigating the Out-Of-Distribution Gap in Natural Language Processing

Most traditional machine learning or deep learning methods are based on the premise that training data and test data are independent and identical distributed, i.e., IID. However, it is just an ideal situation. In real-world applications, test set and training data often follow different distributions, which we refer to as the out of distribution, i.e., OOD, setting. As a result, models trained with traditional methods always suffer from an undesirable performance drop on the OOD test set. It's necessary to develop techniques to solve this problem for real applications. In this dissertation, we present four pieces of works in the direction of OOD in Natural Language Processing (NLP) which can be further grouped into two sub-categories: adversarial robustness and cross-lingual transfer.

Sicheng Yu received the B.E. degree in electronic and information engineering from Dalian University of Technology, China, in 2017 and M.S. degree in signal processing from Nanyang Technology University, Singapore, in 2018. Now he is pursuing the Ph.D. degree in computer science in Singapore Management University under the supervision of Prof. Jing Jiang and Prof. Qianru Sun. His research focuses on natural language processing and causal inference.