Methods and apparatus for identifying a count of N-grams occurring in a corpus

摘要

Methods, apparatuses, systems, and articles of manufacture for identifying a count of N-grams occurring in a body are disclosed herein. An exemplary method involves identifying a token that often starts a suffix found in the corpus. First suffixes and second suffixes are identified within the corpus, with the first suffixes beginning with the token and the second suffix not beginning with the token. A first count algorithm is performed to identify a first count of N-grams occurring in the first suffixes. A second count algorithm is performed to identify a second count of N-grams occurring in the second suffixes. The second counting algorithm differs from the first counting algorithm.