Existing research on Knowledge Base Question Answering (KBQA) typically relies on comprehensive knowledge bases, but often overlooks the critical issue of knowledge graph sparsity in practical applications. To address this shortfall, this study introduces a knowledge representation learning method that transforms knowledge bases into low-dimensional vectors. This transformation effectively eliminates the dependence on subgraph search spaces inherent in traditional models and achieves inference of implicit relationships, which previous research has not explored. Furthermore, to counter the propagation of errors in downstream question-answering inference caused by semantic understanding errors of questions in traditional KBQA information retrieval, this study introduces an answer inference re-ranking mechanism based on knowledge representation learning. This mechanism utilizes pseudo-twin networks to represent knowledge triplets and questions separately, and integrates features from the core entity attention evaluation stage of upstream tasks to effectively re-rank the answer inference result triplets. Finally, to validate the effectiveness of the proposed algorithm, this study conducts comparative experiments on the China Mobile RPA knowledge graph question-answering system and an English open-source dataset. Experimental results demonstrate that, compared to existing models in the same field, this study performs better in multiple key evaluation indicators such as Hits@n, accuracy, and F1 scores, proving the superiority of the proposed KBQA answer inference re-ranking algorithm based on knowledge representation learning in handling implicit relationship inference in sparse knowledge graphs and KBQA answer inference.

[2024-03-11] Accepted Paper /doc/2023.11.0545/v1