We introduce a novel method for bilingual phrase representation with Recurrent Neural Networks (RNNs), which transforms a sequence of word feature vectors into a fixed-length phrase vector across two languages. Our method measures the difference between the vectors of source-and target-side phrases, and can be used to predict the semantic equivalence of source and target word sequences in the phrasal translation units used in phrase-based statistical machine translation. Our experiments show that the proposed method is effective in a bilingual phrasal semantic equivalence determination task and a machine translation task.