Distributional typicality: a new approach to estimating noun and verb usage from large scale text corpora.
Christine Chiarello, Connie Shears, Kevin Lund · PubMed · 2000
This paper reports a new approach to estimating the extent to which words have predominant noun and verb usages which do not require human judgments about parts of speech. The Hyperspace Analog to Language model (HAL, Lund & Burgess, 1996) was used to computationally estimate noun vs verb usage based on the statistical regularities present in a large-scale electronic text corpus. This measure can be used to estimate the extent to which a given word occurs in typical noun or verb sentence contexts (i.e., its distributional typicality) in informal contemporary discourse.