Knowledge Is Flat: A Seq2Seq Generative Framework for Various Knowledge Graph Completion
This addresses the issue of incompatibility and adaptability in KGC models for researchers and practitioners dealing with diverse knowledge graph structures, representing a novel method rather than an incremental improvement.
The authors tackled the problem of Knowledge Graph Completion (KGC) across various graph structures by proposing KG-S2S, a Seq2Seq generative framework that unifies KG facts into flat text, and it outperformed competitive baselines on five benchmarks, setting new state-of-the-art performance.
Knowledge Graph Completion (KGC) has been recently extended to multiple knowledge graph (KG) structures, initiating new research directions, e.g. static KGC, temporal KGC and few-shot KGC. Previous works often design KGC models closely coupled with specific graph structures, which inevitably results in two drawbacks: 1) structure-specific KGC models are mutually incompatible; 2) existing KGC methods are not adaptable to emerging KGs. In this paper, we propose KG-S2S, a Seq2Seq generative framework that could tackle different verbalizable graph structures by unifying the representation of KG facts into "flat" text, regardless of their original form. To remedy the KG structure information loss from the "flat" text, we further improve the input representations of entities and relations, and the inference algorithm in KG-S2S. Experiments on five benchmarks show that KG-S2S outperforms many competitive baselines, setting new state-of-the-art performance. Finally, we analyze KG-S2S's ability on the different relations and the Non-entity Generations.