The method we explore in this paper is illustrated in Figure 1. The overall process has three phrases: we firstly use lexico-syntactic patterns not only to recognize causal relations from the web, but also to identify pairs of event expressions; then, we extract the predicate-argument structure of each event expression based on its dependency parser tree in local scale; in the final phase, we propose a statistical score S to measure the causal association between potential related events, and prune relations with low S value.