Recent text generation methods frequently learn node representations from graph-based data via global or local aggregation, such as knowledge graphs. Since all nodes are connected directly, node global representation encoding enables direct communication between two distant nodes while disregarding graph topology. Node local representation encoding, which captures the graph structure, considers the connections between nearby nodes but misses out onlong-range relations. A quantum-like approach to learning better-contextualised node embeddings is proposed using a fusion model that combines both encoding strategies. Our methods significantly improve on two graph-to-text datasets compared to state-of-the-art models in various experiments.

A quantum-like approach for text generation from knowledge graphs

De Meo P.
Ultimo
2023-01-01

Abstract

Recent text generation methods frequently learn node representations from graph-based data via global or local aggregation, such as knowledge graphs. Since all nodes are connected directly, node global representation encoding enables direct communication between two distant nodes while disregarding graph topology. Node local representation encoding, which captures the graph structure, considers the connections between nearby nodes but misses out onlong-range relations. A quantum-like approach to learning better-contextualised node embeddings is proposed using a fusion model that combines both encoding strategies. Our methods significantly improve on two graph-to-text datasets compared to state-of-the-art models in various experiments.
2023
File in questo prodotto:
File Dimensione Formato  
De Meo-CAAI Trans on Intel Tech - 2023 - A quantum‐like approach for text generation from knowledge graphs.pdf

accesso aperto

Tipologia: Versione Editoriale (PDF)
Licenza: Creative commons
Dimensione 915.97 kB
Formato Adobe PDF
915.97 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11570/3252112
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 6
  • ???jsp.display-item.citation.isi??? 4
social impact