The authors present an algorithm for bilingual word alignment that extends previous work by treating multi-word candidates on a par with single words, and combining some simple assumptions about the translation process to capture alignments for low frequency words. As most other alignment algorithms it uses cooccurrence statistics as a basis, but differs in the assumptions it makes about the translation process. The algorithm has been implemented in a modular system that allows the user to experiment with different combinations and variants of these assumptions. The authors give performance results from two evaluations, which compare well with results reported in the literature. [Based on abstract in book]