🤖 AI Summary
This work addresses cross-document coreference resolution in multi-document knowledge graphs. We propose a knowledge-graph-contextualized dynamic linking mechanism that jointly models entity mentions, knowledge graph structure, and cross-document semantic relations via an integrated framework combining contextual embeddings and graph neural networks, enabling end-to-end entity linking and coreference inference. Our key contributions are: (i) the first integration of knowledge graph embeddings with context-aware graph reasoning for modeling cross-document consistency; and (ii) dynamic updating of entity representations to accommodate heterogeneous, multi-source documents. Evaluated on benchmark datasets—including WD100K and CrossDoc—our method achieves substantial improvements in coreference resolution performance, yielding an average +4.2% F1-score gain over prior approaches. The results demonstrate enhanced capability in multi-document information extraction and knowledge fusion.
📝 Abstract
Coreference resolution across multiple documents poses a significant challenge in natural language processing, particularly within the domain of knowledge graphs. This study introduces an innovative method aimed at identifying and resolving references to the same entities that appear across differing texts, thus enhancing the coherence and collaboration of information. Our method employs a dynamic linking mechanism that associates entities in the knowledge graph with their corresponding textual mentions. By utilizing contextual embeddings along with graph-based inference strategies, we effectively capture the relationships and interactions among entities, thereby improving the accuracy of coreference resolution. Rigorous evaluations on various benchmark datasets highlight notable advancements in our approach over traditional methodologies. The results showcase how the contextual information derived from knowledge graphs enhances the understanding of complex relationships across documents, leading to better entity linking and information extraction capabilities in applications driven by knowledge. Our technique demonstrates substantial improvements in both precision and recall, underscoring its effectiveness in the area of cross-document coreference resolution.