We will present a computational model for determining temporal relations in Chinese. The model takes into account the effects of linguistic features, such as tense/aspect, temporal connectives, and discourse structures, and makes use of the fact that events are represented in different temporal structures. A machine learning approach, Weighted Bayesian Classifier, is developed to map their combined effects to the corresponding relations. An empirical study is conducted to investigate different combination methods, including lexical-based, grammatical-based, and role-based methods. When used in combination, the weights of the features may not be equal. Incorporating with an optimization algorithm, the weights are fine tuned and the improvement is remarkable.