... approximately95% in accuracy and F -measure, and an approx-imate performance of 99.5% in all measures (ac-curacy, precision, recall, F -measure) is achievedby using ME and only some of the features of INIT ... levels of abstraction. Inter-estingly, INIT achieves the same (and slightly bet-ter) accuracy as Wan et al.’s system, without em-ploying any parsing. Our more enhanced methods,INIT+WN and INIT+WN+DEP, ... metrics, ratherthan string similarity measures, unlike our system.We plan to examine further how the features of Finch et al. and other ideas from machine trans-lation can be embedded in our system,...