This project investigates a technique called TF-partitioned signature file, for supporting document ranking with signature files. Multiple signature files are employed, each of which corresponds to a particular term frequency, to represent terms with different term frequencies. Words with the same term frequency in a document are grouped together and hased into the signature file corresponding to that term frequency. This eliminates the need to explicitly record the term frequency for each word. The effect of false drops, if not eliminated in the search process, on retrieval effectiveness is studied.