Learn More
We describe a program that uses statistical information on word-usage to perform syntactic disambiguation, and show that the use of this information signiicantly improves performance. The bulk of the paper, however, attempts to answer the question: what did the program learn that would account for this improvement? We show that the program has learned many(More)
In this paper we tried to describe some implemented programs that extract gram­ matical information about English from a large untagged corpus. Using statistical techniques we generated the case frames of verbs, and the obligatory and optional prepositions attached to nouns and adjectives, which we believe are of great impor­ tance for parsers and(More)
  • 1