Traditional information retrieval (IR) approaches assume that the indexing terms are independent, which is not true in reality. Although some previous studies have tried to consider term relationships, strong simplifications had to be made at the very basic indexing step, namely, dependent terms are assigned independent counts or probabilities. In this study, we propose to consider dependencies between terms using Dempster-Shafer theory of evidence. An occurrence of a string in a document is considered to represent the set of all the terms implied in it. Probability is assigned to such a set of terms instead of individual terms. During query evaluation phase, a part of the probability of a set can be transferred to those of the query that are related, allowing us to integrate language-dependent relations in IR. This approach has been tested on several Chinese IR collections. Our experimental results show that our model can outperform the existing state-of-the-art approaches. The proposed method can be used as a general way to consider different types of relationship between terms and for other languages.