... research to compare them, as described be-low. To assess each extraction, we determine how sim-ilar its context vector is to a canonical seed vec-tor (created by summing the context vectors of the seeds). ... et al., 2007). In ad-dition to locating the proper nouns in the corpus,LEX also concatenates each multi-token proper noun(e.g.,Los Angeles) together into a single token.Both of REALM’s components ... argument of the type City, to the seedargument Chicago, for which the following twophrases appear in the corpus:(i) “Pickerington, Ohio”(ii) “Chicago, Illinois”In these phrases, the textual...