... modest recall. As a result, large quantities of NE instances are automatically acquired. An automatically annotated NE corpus can then be constructed by extracting the tagged instances plus ... recall. Then, these rules are applied to a large raw corpus to automatically generate a tagged corpus. Finally, an HMM-based NE tagger is trained using this corpus. There is no iterative learning ... containsDigitAndAlpha, containsDigitAndDash, containsDigitAndSlash, containsDigitAndComma, containsDigitAndPeriod, otherNum, allCaps, capPeriod, initCap, lowerCase, other. 6 Benchmarking and...