Community Question Answering (CQA) services, such as Yahoo! Answers and WikiAnswers, have become popular with users as one of the central paradigms for satisfying users' information needs. The task of question retrieval aims to answer one's query directly by finding the most relevant questions (together with their answers) from an archive of past questions. However, questions are always short text that there is a lexical gap between the queried question and the past questions. Furthermore, the underlying intents of two questions could be very different even if they bear a close lexical resemblance. To alleviate these problems, we present a hybrid approach that blends several language modelling techniques for question retrieval, namely, the Classic (query-likelihood) Language Model, the state-of-the-art Translation-based Language Model, and our proposed Semantic-based Language Model and Intent-based Language Model. The semantics of each candidate question is derived by a Probabilistic Topic Model, which makes use of local and global semantic graphs for capturing the hidden interactions among entities (e.g. people, places and concepts) in question-answer pairs. Experiments on two real-world data sets show that our approach can significantly outperform existing ones.