US 12,032,916 B2
Structure self-aware model for discourse parsing on multi-party dialogues
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 Feb. 22, 2021, as Appl. No. 17/181,431.
Prior Publication US 2022/0269868 A1, Aug. 25, 2022
Int. Cl. G06F 40/35 (2020.01); G06F 17/16 (2006.01); G06N 3/049 (2023.01)
CPC G06F 40/35 (2020.01) [G06F 17/16 (2013.01); G06N 3/049 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of dialogue parsing, executable by a processor, comprising:
receiving dialogue data having one or more elementary discourse units;
initializing nodes and edges of a structural self-aware graph neural network (SSA-GNN) based on the one or more elementary discourse units;
determining a local representation, by multiple bidirectional gated recurrent units (GRUs) consuming each utterance represented by the one or more elementary discourse units and then concatenating a last hidden state in the multiple GRUs, and a global representation, by applying another bidirectional GRU on the local representations, for each of the elementary discourse units;
generating, in a neural network, at least one edge-specific vector representing an edge between a pair of elementary discourse units, the at least one edge-specific vector being generated based on the determined local and global representations, the at least one edge-specific vector capturing relation information for the pair of elementary discourse units;
identifying relationships between the elementary discourse units based on the at least one edge-specific vector generated in the neural network and based on structure-aware scaled dot-product attention of the SSA-GNN and a layer-wise classifier on edge hidden states of each SSA-GNN layer; and
predicting a contextual link between non-adjacent elementary discourse units based on the identified relationships.