Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
This work addresses the need for more accurate and flexible NKG construction, which is crucial for applications requiring complex real-world facts, though it appears incremental as it builds on existing NKG schemas.
The paper tackles the problem of constructing n-ary relational knowledge graphs (NKGs) from text, which often involves coarse-grained extraction ignoring entity order and variable arity, by proposing Text2NKG, a fine-grained n-ary relation extraction framework that achieves state-of-the-art F1 scores on a benchmark.
Beyond traditional binary relational facts, n-ary relational knowledge graphs (NKGs) are comprised of n-ary relational facts containing more than two entities, which are closer to real-world facts with broader applications. However, the construction of NKGs remains at a coarse-grained level, which is always in a single schema, ignoring the order and variable arity of entities. To address these restrictions, we propose Text2NKG, a novel fine-grained n-ary relation extraction framework for n-ary relational knowledge graph construction. We introduce a span-tuple classification approach with hetero-ordered merging and output merging to accomplish fine-grained n-ary relation extraction in different arity. Furthermore, Text2NKG supports four typical NKG schemas: hyper-relational schema, event-based schema, role-based schema, and hypergraph-based schema, with high flexibility and practicality. The experimental results demonstrate that Text2NKG achieves state-of-the-art performance in F1 scores on the fine-grained n-ary relation extraction benchmark. Our code and datasets are publicly available.