This article proposes a new general, highly efficient algorithm for extracting domain terminologies.This domain-independent algorithm with multi-layers of filters is a hybrid of statistic-oriented and rule-oriented methods. Utilizing the features of domain terminologies and the characteristics that are unique to Chinese, this algorithm extracts domain terminologies by generating multi-word unit (MWU) candidates at first and then filtering the candidates through multi-strategies. Our test results show that this algorithm is feasible and effective.