Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs

Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting graph topology as all nodes are directly connected... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Data-to-Text Generation AGENDA CGE-LW BLEU 18.01 # 1
Graph-to-Sequence WebNLG CGE-LW BLEU 63.69 # 1
Data-to-Text Generation WebNLG CGE-LW BLEU 0.636 # 4

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet