Improving Knowledge Graph Embedding Using Locally and Globally Attentive Relation Paths

Abstract

Knowledge graphs' incompleteness has motivated many researchers to propose methods to automatically infer missing facts in knowledge graphs. Knowledge graph embedding has been an active research area for knowledge graph completion, with great improvement from the early TransE to the current state-of-the-art ConvKB. ConvKB considers a knowledge graph as a set of triples, and employs a convolutional neural network to capture global relationships and transitional characteristics between entities and relations in the knowledge graph. However, it only utilizes the triple information, and ignores the rich information contained in relation paths. In fact, a path of one relation describes the relation from some aspect in a fine-grained way. Therefore, it is beneficial to take relation paths into consideration for knowledge graph embedding. In this paper, we present a novel convolutional neural network-based embedding model PConvKB, which improves knowledge graph embedding by incorporating relation paths locally and globally. Specifically, we introduce attention mechanism to measure the local importance of relation paths. Moreover, we propose a simple yet effective measure DIPF to compute the global importance of relation paths. Experimental results show that our model achieves substantial improvements against state-of-the-art methods.

Knowledge-infused Learning for Entity Prediction in Driving Scenes

“…This may be a consequence of HolE’s ability to handle graph patterns with higher instance cardinality, as it can represent 1-to-N, N-to-1 and N-to-N relations through circular correlation (⋆) (see scoring function in Table 4 ). TransE, however, lacks this ability to represent such relations and ConvKB suffers from the same as it can be considered as a DL-based extension of TransE ( Jia et al, 2020 ).…”

“…For these reasons, our approach for KEP involves learning KGEs using several KGE algorithms and re-using the learned latent space for KEP. For this task, our KGE algorithm selection strategy is two-fold: 1) select one popular ( Jia et al, 2020 ) representative algorithm from each of the three classes mentioned in Section 2.3 , and 2) select algorithms with space and time complexities lower than , efficient enough to conduct multiple experiments. Considering these criteria, 3 KGE algorithms are selected for experimentation: TransE, HolE, and ConvKB.…”

Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network

“…Subsequent work proposed several mechanisms to solve this problem: (1) labeling tagging sequences for words (Dai et al, 2019) or entities (Yu et al, 2019;Wei et al, 2020); (2) transforming the sentence into a graph structure (Wang et al, 2018;; (3) generating triple element sequences with copy mechanism (Zeng et al, 2018(Zeng et al, , 2019(Zeng et al, , 2020Nayak and Ng, 2020); (4) linking token pairs with a handshake tagging scheme (Wang et al, 2020). However, these methods usually ignored implicit relational triples that are not directly expressed in the sentence (Zhu et al, 2019), thus will lead to the incompleteness of the resulting KGs and negatively affect the performance of downstream tasks (Angeli and Manning, 2013;Jia et al, 2020).…”

“…For example, in Figure 1, the explicit triples are strongly indicated by the key relational phrases, but the implicit relation "Live in" is not expressed explicitly. Unfortunately, existing methods usually ignored implicit triples (Zhu et al, 2019), which will cause serious incompleteness of the constructed KGs and performance degradation of downstream tasks (Angeli and Manning, 2013;Jia et al, 2020;Jun et al, 2020).…”

Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and Graph

“…For example, in Figure 1, the triple ("David", "father", "Judy") is not explicitly expressed in the sentence and requires relational reasoning to be extracted. Unfortunately, the ignorance of relational reasoning patterns in existing methods will cause serious incompleteness of the constructed KGs and performance degradation of downstream tasks (Angeli and Manning, 2013;Jia et al, 2020).…”