US 12,086,552 B2
Generating semantic vector representation of natural language data
Thanh Lam Hoang, Maynooth (IE); Gabriele Picco, Dublin (IE); and Vanessa Lopez Garcia, Dublin (IE)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Mar. 24, 2022, as Appl. No. 17/656,418.
Prior Publication US 2023/0306203 A1, Sep. 28, 2023
Int. Cl. G06F 40/30 (2020.01); G06F 40/205 (2020.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06N 5/022 (2023.01)
CPC G06F 40/30 (2020.01) [G06F 40/205 (2020.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for automatically generating a semantic vector representation of a relation between a specific set of entities in natural language text, comprising:
in response to receiving a text segment comprising a set of entities, automatically parsing the text segment into an abstract meaning representation (AMR) graph comprising nodes representing the set of entities;
extracting a number of trees from the AMR graph, wherein the number of trees comprises minimum Steiner trees, wherein each minimum Steiner tree represents a path and tree between a first entity and at least one second entity from the set of entities, and wherein each Steiner tree comprises a minimum amount of edges between the nodes corresponding to the first entity and the at least one second entity;
using a trained graph neural network (GNN) to determine vector embeddings for each of the extracted number of minimum Steiner trees; and
in response to receiving the vector embeddings returned by the trained GNN, aggregating the vector embeddings to generate the semantic vector representation of the relation between the specific set of entities.