@techreport{ilprints554,
          number = {2002-46},
           month = {April},
          author = {Joseph Smarr and Christopher D. Manning},
           title = {Classifying Unknown Proper Noun Phrases Without Context},
            type = {Technical Report},
       publisher = {Stanford},
     institution = {Stanford InfoLab},
            year = {2002},
        keywords = {named-entity classification, unknown words, probabilistic modeling, n-grams},
             url = {http://ilpubs.stanford.edu:8090/554/},
        abstract = {We present a probabilistic generative model used to classify unknown Proper Noun Phrases into semantic categories.  The core of the classifier is an n-gram character model, which is enhanced with an n-gram word-length model and a common word model.  While most work has depended largely on context or domain-specific rules for semantic disambiguation of unknown names, we demonstrate that there is surprisingly reliable statistical information available in the composition of the names themselves.  Using the context-independent probabilities assigned by our domain independent classifier is sufficient to achieve greater than 90% classification accuracy on typical tasks.}
}