Knowledge-based question answering using graph neural networks and contextual language representations

Abstract This work introduces a novel question answering (QA) framework that integrates commonsense knowledge from ConceptNet with deep contextual embeddings from BERT using a graph neural network for structured reasoning. For each question–answer pair, the system constructs a relevant subgraph from...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Mohamed Samir, Naglaa Fathy, Walaa Gad
Format:	Artigo
Sprog:	Inglês
Udgivet:	Nature Portfolio 2026-01-01
Serier:	Scientific Reports
Fag:	Knowledge graph Graph neural networks Language models Question answering QA system
Online adgang:	https://doi.org/10.1038/s41598-025-33854-2
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!