US 12,229,505 B2
Structural information preserving for graph-to-text generation
Linfeng Song, Palo Alto, CA (US)
Assigned to TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed by TENCENT AMERICA LLC, Palo Alto, CA (US)
Filed on Dec. 5, 2022, as Appl. No. 18/075,090.
Application 18/075,090 is a continuation of application No. 16/883,475, filed on May 26, 2020, granted, now 11,550,997.
Prior Publication US 2023/0099150 A1, Mar. 30, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/20 (2020.01); G06F 16/901 (2019.01); G06F 40/30 (2020.01); G06N 3/08 (2023.01); G06N 20/00 (2019.01)
CPC G06F 40/20 (2020.01) [G06F 16/9024 (2019.01); G06F 40/30 (2020.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A method of training a graph-to-text generation network, comprising:
receiving graph information corresponding to a target sentence, wherein the graph information includes one or more grounded triples corresponding to the target sentence;
decoding the graph information based on a biaffine attention score;
determining a first loss based on alignments between one or more nodes and target words;
determining a second loss, wherein a loss of graph structural information is associated with the second loss, wherein the loss of graph structural information associated with the second loss is minimized using a depth-first traversal; and
training a graph-to-text model based on the first loss and the second loss.