US 11,694,035 B2
Hypernym detection using strict partial order networks
Sarthak Dash, Jersey City, NJ (US); Alfio Massimiliano Gliozzo, Brooklyn, NY (US); and Md Faisal Mahbub Chowdhury, Woodside, NY (US)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Jun. 9, 2021, as Appl. No. 17/343,643.
Application 17/343,643 is a continuation of application No. 16/575,107, filed on Sep. 18, 2019, granted, now 11,068,665.
Prior Publication US 2021/0303800 A1, Sep. 30, 2021
Int. Cl. G06F 40/30 (2020.01); G06N 3/08 (2023.01)
CPC G06F 40/30 (2020.01) [G06N 3/08 (2013.01); G06F 2207/4824 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving a list of candidate hyponym-hypernym pairs extracted from a text corpus, wherein each candidate hyponym-hypernym pair comprises a pair of terms representing a candidate hyponym and a candidate hypernym;
modifying the list to add or remove at least one candidate hyponym-hypernym pair; and
training, via machine learning, a neural network for hypernym induction based on the modified list and frequency information indicative of a number of times a hypernymy relation is observed between a candidate hyponym and a candidate hypernym of each candidate hyponym-hypernym pair of the modified list, wherein the trained neural network is a strict partial order network (SPON).