Fine-Grained Entity Typing via Hierarchical Multi Graph Convolutional Networks

Abstract

This paper addresses the problem of inferring the fine-grained type of an entity from a knowledge base. We convert this problem into the task of graph-based semi-supervised classification, and propose Hierarchical Multi Graph Convolutional Network (HMGCN), a novel Deep Learning architecture to tackle this problem. We construct three kinds of connectivity matrices to capture different kinds of semantic correlations between entities. A recursive regularization is proposed to model the subClassOf relations between types in given type hierarchy. Extensive experiments with two large-scale public datasets show that our proposed method significantly outperforms four state-of-the-art methods.

Diversified Semantic Attention Model for Fine-Grained Entity Typing

“…Compared to the second highest Macro-F1 score of Attentive+LTR [36], our DSAM approach achieved a 0.29% higher score (83.29% vs. 83.00%). Our DSAM approach achieved a much higher Accuracy and Macro-F1 score than HMGCN [25] but performed worse based on the Micro-F1 score (69.44% vs. 57% in Accuracy, 83.29% vs. 79.8% based on the Macro-F1 score and 81.46% vs. 83.6% based on the Micro-F1 score). This is due to the fact that three GCN models proposed in the HMGCN provide complementary information, which makes its performance based on the Micro F1 score slightly better than ours.…”

“…For example, Jin et al [24] used links between entities to construct an entity graph, and jointly utilized entity features and a graph structure to make an entity type inference. Later, they further proposed a novel architecture [25] consisting of three graph convolutional networks to capture different kinds of semantic correlations between entities to refine entity types. Although distant supervisionbased methods provide an efficient way to annotate training data, they ignore the local contextual information associated with entities and limit its usage in context-aware applications.…”

Knowledge Association with Hyperbolic Knowledge Graph Embeddings

“…For JOIE, we choose its best-performing variant based on the translational encoder with cross-view transformation. A related method (Jin et al, 2019) is not taken into comparison as it requires entity attributes that are unavailable in our problem setting.…”

“…(ii) Auxiliary information. Besides relational structures, some studies characterize entities based on auxiliary information, including numerical attributes Trisedya et al, 2019), literals (Gesese et al, 2019 and descriptions Chen et al, 2018;Jin et al, 2019). They capture associations based on alternative resources, but are also challenged by the less availability of auxiliary information in many KGs (Speer et al, 2017;Mitchell et al, 2018).…”

“…Challenged by the diverse schemata, relational structures and granularities of knowledge representations in different KGs (Nikolov et al, 2009), traditional symbolic methods usually fall short of supporting heterogeneous knowledge association (Suchanek et al, 2011;Lacoste-Julien et al, 2013;Paulheim and Bizer, 2013). Recently, increasing efforts have been put into exploring embeddingbased methods (Chen et al, 2017;Trivedi et al, 2018;Jin et al, 2019). Such methods capture the associations of entities or concepts in a vector space, which can help overcome the symbolic and schematic heterogeneity .…”