I propose a general algorithm for detecting translational equivalence between text samples in different languages. This algorithm is based on current approaches to duplicate detection, and it relies on information which can be automatically learned from parallel text. I also show experimental results which support the hypothesis that translational equivalence is empirically observable. In addition, these results suggest profitable directions for improving performance on this recognition task. Cross-referenced as UMIACS-TR-2001-36 Cross-referenced as LAMP-TR-071