I am a research scientist at the Content Integrity NLP team since 2018. My research mainly focuses on combining integrity-domain knowledge with state-of-the-art NLP technology to reduce bad user experience from objectionable and harmful contents. Before joining Facebook I got a PhD at the University of Rochester. My advisor is Prof. Daniel Gildea. My PhD research focuses on machine learning and statistical methods towards machine translation and semantic parsing.
Natural language processing, language modeling, domain adaptation, structured prediction, deep learning
Workshop on Abusive Language Online - August 1, 2019
Fan Yang, Xiaochang Peng, Gargi Ghosh, Reshef Shilon, Hao Ma, Eider Moore, Goran Predovic
Computational Linguistics - June 1, 2019
Hao Zhang, Richard Sproat, Axel H. Ng, Felix Stahlberg, Xiaochang Peng, Kyle Gorman, Brian Roark