Relevant Entity Selection: Knowledge Graph Bootstrapping via Zero-Shot Analogical Pruning
This addresses scalability and relevance issues in knowledge graph construction for researchers and practitioners working with large-scale knowledge bases.
The paper tackles the problem of selecting relevant entities from large knowledge graphs for knowledge graph construction by proposing a zero-shot analogical pruning method. The approach outperforms LSTM, Random Forest, SVM, and MLP baselines with significantly fewer parameters, as demonstrated on Wikidata datasets.
Knowledge Graph Construction (KGC) can be seen as an iterative process starting from a high quality nucleus that is refined by knowledge extraction approaches in a virtuous loop. Such a nucleus can be obtained from knowledge existing in an open KG like Wikidata. However, due to the size of such generic KGs, integrating them as a whole may entail irrelevant content and scalability issues. We propose an analogy-based approach that starts from seed entities of interest in a generic KG, and keeps or prunes their neighboring entities. We evaluate our approach on Wikidata through two manually labeled datasets that contain either domain-homogeneous or -heterogeneous seed entities. We empirically show that our analogy-based approach outperforms LSTM, Random Forest, SVM, and MLP, with a drastically lower number of parameters. We also evaluate its generalization potential in a transfer learning setting. These results advocate for the further integration of analogy-based inference in tasks related to the KG lifecycle.