We propose a novel unsupervised keyphrase extraction approach based on outlier detection. Our approach starts by training word embeddings on the target document to capture semantic regularities among the words. It then uses the minimum covariance determinant estimator to model the distribution of non-keyphrase word vectors, under the assumption that these vectors come from the same distribution, indicative of their irrelevance to the semantics expresses by the dimensions of the learned vector representation. Candidate keyphrases are based on words that are outliers of this dominant distribution. Empirical results show that our approach outperforms state-of-the-art unsupervised keyphrase extraction methods.