The task of knowledge graph entity typing (KGET) aims to infer the missing types for entities in knowledgegraphs, which is a significant subtask of knowledgegraph completion (KGC). In despite of its progress, we obs...
详细信息
knowledge graph entity typing is an important way to complete knowledgegraphs (KGs), aims at predicting the associating types of certain given entities. However, previous methods suppose that many (entity, entity typ...
详细信息
ISBN:
(纸本)9781450387477
knowledge graph entity typing is an important way to complete knowledgegraphs (KGs), aims at predicting the associating types of certain given entities. However, previous methods suppose that many (entity, entity type) pairs can be obtained for each entity type, performing poorly on entity types that only have a few associative entities. Besides, these methods cannot fully exploit the inherent correlation and complementarity information across different entities sharing the same entity type. To this end, we propose a novel model named Contrastive entitytyping (CET) for KG entity tying. CET can better learn the mutual interactions among the entities with the same entity type and can fully utilize the hierarchical information in entity type trees by two contrastive learning modules. The main benefit of the proposed contrastive learning modules is that they can effectively encourage the consistency of the entity representations with the same type while improving the discriminability of the entity type classifiers. Empirically, our model achieves state-of-the-art results on KG entitytyping benchmarks.
knowledge graph entity typing (KGET) is a subtask of knowledgegraph completion, which aims at inferring missing entity types by utilizing existing type knowledge and triple knowledge of the knowledgegraph. Previous ...
详细信息
knowledge graph entity typing (KGET) is a subtask of knowledgegraph completion, which aims at inferring missing entity types by utilizing existing type knowledge and triple knowledge of the knowledgegraph. Previous knowledgegraph embedding (KGE) algorithms infer entity types through trained entity embeddings. However, for new unseen entities, KGE models encounter obstacles in inferring their types. In addition, it is also difficult for KGE models to improve the performance incrementally with the increase of added data. In this paper, we propose a statistic-based KGET algorithm which aims to take both performance and incrementality into consideration. The algorithm aggregates the neighborhood information and type co-occurrence information of target entities to infer their types. Specifically, we first compute the type probability distribution of the target entity in the semantic context of given fact triple. Then the probability information of fact triples involved in the target entity is aggregated. In addition to local neighborhood information, we also consider capturing global type co-occurrence information for target entities to enhance inference performance. Extensive experiments show that our algorithm outperforms previous statistics-based KGET algorithms and even some KGE models. Finally, we design an incremental inference experiment, which verifies the superiority of our algorithm in predicting the types of new entities, and the experiment also verifies that our algorithm has excellent incremental property.
knowledge graph entity typing (KGET) aims to infer missing entitytyping instances in KGs, which is a significant subtask of KG completion. Despite of its progress, however, we observe that it still faces two non-triv...
详细信息
knowledge graph entity typing (KGET) aims to infer missing entitytyping instances in KGs, which is a significant subtask of KG completion. Despite of its progress, however, we observe that it still faces two non-trivial challenges: (i) most existing KGET methods extract features by encoding the existing entitytyping tuples, while underutilizing or even ignoring rich relational knowledge. (ii) they typically treat each entitytyping tuple in KGs independently, and thus inevitably fail to take account of the inherent and valuable neighborhood information surrounding a tuple. To address these challenges, we build a novel Heterogeneous Relational graph (HRG), and propose a Multiplex Relational graph Attention Networks (MRGAT) to learn on HRG, and then utilize a Connecting Embeddings model (ConnectE) to make entity type inference. Specifically, the overall framework contains three significant components. First, to effectively integrate the heterogeneous structural information including the entitytyping tuples and entity relation triples in KGs, we construct a heterogeneous relational graph that consists of three semantic subgraphs. Second, we employ MRGAT to learn embeddings on HRG. In MRGAT, each subgraph of HRG is fed to its corresponding model that is capable of capturing neighborhood information by aggregating the surrounding nodes' features. Finally, given the learned embeddings, we make entity type prediction by the connecting embeddings method ConnectE. Experimental results demonstrate the effectiveness of our proposed model against various state-of-the-art baselines.
knowledge graph entity typing (KGET) aims to predict the missing entity types in knowledgegraphs (KG). The relationship between entities and their corresponding types is often expressed using a single relation, hasTy...
详细信息
ISBN:
(纸本)9798400704901
knowledge graph entity typing (KGET) aims to predict the missing entity types in knowledgegraphs (KG). The relationship between entities and their corresponding types is often expressed using a single relation, hasType. However, hasType has a limited capability for modeling diverse entity-type relationships in the embedding space. In this paper, we first introduce multiple auxiliary relations to model the complex entity-type relationship. We propose an efficient and robust algorithm to group similar entity types together and assign a unique auxiliary relation to each group. Then, with the auxiliary relations, we propose an Asynchronous representation learning framework for KGET, named AsyncET, where entity and type embeddings are updated alternatively. Consequently, the quality of entity embeddings is gradually improved during training by infusing type information. In addition, entity types with different granularities and semantics can be properly modeled in the embedding space. Experimental results show that AsyncET can substantially improve the performance of embedding-based methods on the KGET task and has a significant advantage over state-of-the-art neural network-based methods in terms of model sizes and inference time.
knowledge graph entity typing, which is an important way to complete knowledgegraphs (KGs), aims at predicting the associating type of certain given entities without any external knowledge. However, previous methods ...
详细信息
ISBN:
(数字)9783031059339
ISBN:
(纸本)9783031059339;9783031059322
knowledge graph entity typing, which is an important way to complete knowledgegraphs (KGs), aims at predicting the associating type of certain given entities without any external knowledge. However, previous methods suppose that many (entity, entity type) pairs (ETPs) can be obtained for each entity type, performing poorly on entity types that only have a few associative entities and do not fully utilize the internal information in KGs. In this work, we propose a novel model named Meta entitytyping (MET) for few-shot knowledge graph entity typing. In MET, we achieve knowledge graph entity typing by meta-learning with three sub-tasks formed by the hierarchical entity type tree in its meta-training stage. In this way, MET can focus on transferring type-specific meta information to learn the most important knowledge for entitytyping. Besides, to fully employ the internal information in KGs given limited ETPs, inspired by Factorization Machines, we design a novel Relation To Relation graph Convolutional Networks (R2R-GCN), in which we consider different relation combinations could have distinct influence on its corresponding entity, R2R-GCN can explicitly model the interactions between different relations. Empirically, our model achieves state-of-the-art results on few-shot entitytyping KG benchmarks.
knowledge graph entity typing (KGET) is an efficient way to infer possible missing types for entities, which has become a key instrument to enhance the construction of knowledgegraphs (KGs). Existing models to KGET h...
详细信息
knowledge graph entity typing (KGET) is an efficient way to infer possible missing types for entities, which has become a key instrument to enhance the construction of knowledgegraphs (KGs). Existing models to KGET have mainly focused on a single granularity information such as distinct entity information, but other granularity information including entity-to-type-clusters, the same cluster and interaction information have not been fully explored, resulting in inferring incorrect types in KGs. To address this, we propose a GPT-assisted Multi-Granularity Contrastive Learning (GMGCL) approach to acquire entity-to-type-clusters, entity, type-cluster and relation information by GPT-assisted entity-to-type-clusters clustering, entity-based, cluster-based and relation-based contrastive learning, respectively. Our approach is evaluated on FB15kET and YAGO43kET datasets, outperforming other baselines and obtaining a 1.35% average improvement at least on MRR.
暂无评论