US 11,657,229 B2
Using a joint distributional semantic system to correct redundant semantic verb frames
Yunyao Li, San Jose, CA (US); Carlos Fernando Diez Sánchez, Mexico City (MX); and Marie Louise Elizabeth van der Plas, San Gwann (MT)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on May 19, 2020, as Appl. No. 16/878,352.
Prior Publication US 2021/0365636 A1, Nov. 25, 2021
Int. Cl. G06F 17/00 (2019.01); G06F 40/30 (2020.01); G06F 17/16 (2006.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06F 40/30 (2020.01) [G06F 17/16 (2013.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 22 Claims
OG exemplary drawing
 
21. A computer-implemented method, comprising:
given a list of pairs of first automatically projected semantic verb frames and redundancy labels associated with the first automatically projected semantic verb frames, for each of the pairs of first automatically projected semantic verb frames: computing a similarity score;
training a joint distributional semantic system using the redundancy labels and the computed similarity scores;
receiving pairs of second automatically projected semantic verb frames;
applying the trained joint distributional semantic system to the pairs of the second automatically projected semantic verb frames; and
merging at least some of the pairs of the second automatically projected semantic verb frames, based on results of applying the joint distributional semantic system.