Fact retrieval from knowledge graphs through semantic and contextual attention

Knowledge Graphs (KGs), such as DBpedia and ConceptNet, enhance Natural Language Processing (NLP) applications by providing structured information. However, extracting accurate data from KGs is challenging due to issues in entity detection, disambiguation, and relation classification, which often lead to errors and inefficiencies. We introduce Attention2Query (A2Q), an attention-driven approach that directly ranks and selects the most relevant facts, thus minimizing error propagation. A2Q centres on three key contributions: (1) Focused Node Selection, which streamlines graph traversal; (2) Global Attention Alignment, improving retrieval by comparing facts against the query text; and (3) Contextual Re-ranking, enabling on-the-fly adjustments of fact importance based on evolving query context. Experimental results across multiple tasks and datasets show that A2Q substantially outperforms baseline methods, including those in zero-shot settings, achieving higher retrieval accuracy with reduced computational overhead.