Described are computer-based methods and apparatuses, including computer program products, for automation of auditing claims. A data file is received comprising one or more auditable items, each auditable item comprising a word string having one or more words. Each word string for each auditable item is translated using one or more translation steps into a translated item description. Each translated item description is compared to a plurality of terms to generate matching information. Each translated item description is associated with an item identifier based on the matching information. Each auditable item is accepted or rejected based on the item identifier and one or more rules associated with the data file.