×

Method and system for deriving a large-span semantic language model for large-vocabulary recognition systems

  • US 5,828,999 A
  • Filed: 05/06/1996
  • Issued: 10/27/1998
  • Est. Priority Date: 05/06/1996
  • Status: Expired due to Term
First Claim
Patent Images

1. A method for deriving a large-span semantic language model for a large vocabulary recognition system, the method comprising the steps of:

  • (a) mapping words into a vector space, where each word is represented by a vector;

    (b) clustering the vectors into a set of clusters, where each cluster represents a semantic event;

    (c) computing a first probability that a first word will occur given a history of prior words by,(i) calculating a second probability that a vector representing the first word belongs to each of the clusters, the second probability capable of being independent of a location of the first word in a sentence;

    (ii) calculating a third probability of each cluster occurring in a history of prior words; and

    (iii) weighting the second probability by the third probability.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×