Welcome to my homepage! I am Kai Sun (孙锴), a Ph.D. student at Cornell University, studying Computer Science. My advisor is Claire Cardie. Before coming to Cornell, I did my undergraduate studies in Computer Science, in the ACM Honored Class 2011 at Shanghai Jiao Tong University.
I am interested in artificial intelligence (AI) related areas including speech and natural language processing, machine learning, and AI in games.
Belief and Sentiment Detection
Our team participated in the BeSt Evaluation at the 2016 NIST TAC KBP. Our system ranked the 1st in 6 of 8 Chinese tasks, and 2 of 8 English tasks.
Our team participated in the 2nd DSTC (Dialog State Tracking Challenge) and ranked the 3rd; In the 3rd DSTC, our method was found to be one of the top three tracking methods (ranked 1st/2nd/3rd in "requested slots"/"method"/"joint goals" respectively), and was one of the only two methods that outperformed all four baselines of the challenge; In the 4th DSTC, our team ranked the 2nd.
AI in Board Games
Yixin, a state-of-the-art Gomoku/Renju program designed by me, is the winner of the 13th, 14th, 15th, 16th and 17th Gomocup, significantly outperforming the AI in the second position with a gap of about 300 elo, and is currently the strongest Gomoku/Renju program in the world.
Qizhe Xie, Kai Sun, Su Zhu, Lu Chen and Kai Yu. Recurrent Polynomial Network for Dialogue State Tracking with Mismatched Semantic Parsers. 16th Annual SIGdial Meeting on Discourse and Dialogue (SIGdial). 2015. pdf bib
Kai Yu, Kai Sun, Lu Chen and Su Zhu. Constrained Markov Bayesian Polynomial for Efficient Dialogue State Tracking. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP). 2015. pdf bib