Combining linguistic features with weighted Bayesian classifier for temporal reference processing

Temporal reference is an issue of determining how events relate to one another. Determining temporal relations relies on the combination of the information, which is explicit or implicit in a language. This paper reports 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.