|Qizhe Xie, Kai Sun, Su Zhu, Lu Chen and Kai Yu|
Recently, constrained Markov Bayesian polynomial (CMBP) has been proposed as a data-driven rule-based model for dialog state tracking (DST). CMBP is an approach to bridge rule-based models and statistical models. Recurrent Polynomial Network (RPN) is a recent statistical framework taking advantages of rulebased models and can achieve state-of-the-art performance on the data corpora of DSTC-3, outperforming all submitted trackers in DSTC-3 including RNN. It is widely acknowledged that SLU’s reliability influences tracker’s performance greatly, especially in cases where the training SLU is poorly matched to the testing SLU. In this paper, this effect is analyzed in detail for RPN. Experiments show that RPN’s tracking result is consistently the best compared to rule-based and statistical models investigated on different SLUs including mismatched ones and demonstrate RPN’s is very robust to mismatched semantic parsers.