NSTL国家科技图书文献中心

1. HieRelBERT: Enhanced Lexical Relation Embedding Based-On Hierarchical Contrast Learning NSTL国家科技图书文献中心

Liping Li | Yexuan Zhang ... - 《Computational and Experimental Simulations in Engineering,Volume 4》 - International Conference on Computational & Experimental Engineering and Sciences - 2025, - 795～815 - 共21页

摘要：. In this paper, we propose a novel lexical relation | embedding approach grounded in hierarchical contrastive | Understanding the lexical relationships | between word pairs is paramount for advancing | applications in natural language processing. However

关键词： Lexical relation | Contrast learning | Prompt learning

2. AttRel: Single Module Based Joint Entity and Relation Extraction with Attention Enhanced Text Embedding NSTL国家科技图书文献中心

Mengmeng Cui | Chenbin Li ... - 《Advanced Data Mining and Applications,Part V》 - International Conference on Advanced Data Mining and Applications - 2025, - 328～343 - 共16页

摘要： exploit the rich semantic information in relation* labels* | as relation* prior knowledge, which can provide* | understand entity relations, classify relation* labels, and* | enhance the accuracy of joint entity and relation | embedding, named AttRel. Specifically, a novel single

关键词： Joint extraction | Attention mechanisms | Relation embedding

3. Concepts and Relations Features Are All You Need for Embedding-Based Ontology Matching NSTL国家科技图书文献中心

Samira Oulefki | Lamia Berkani ... - 《Web Information Systems Engineering - WISE 2024,Part I》 - International Conference on Web Information Systems Engineering - 2025, - 416～430 - 共15页

摘要： embedding-based OM approaches, GATHER excels by seamlessly | embedding matcher. Extensive experiments across multiple | Ontology matching (OM) is one of the most | challenging problems in the Semantic Web. Despite | significant progress over the past few decades, evidenced by

关键词： Ontology matching | Graph transformer | Relational graph transformer | Relation embedding generation

4. GeoEntity-type constrained knowledge graph embedding for predicting natural-language spatial relations NSTL国家科技图书文献中心

Lei Hu | Wenwen Li ... - 《International journal of geographical information science》 - 2025,39(1/2) - 376～399 - 共24页

摘要： overcome this limitation, we developed a Spatial Relation | -based Knowledge Graph Embedding* framework, SR-KGE* | relation terms among distinct geoentities. This method | diversity of natural language expressions in the embedding | performance in spatial relation* inference compared to*

关键词： Spatial relation | natural language | knowledge graph embedding | joint training

5. Contextualizing Entity Representations for Zero-Shot Relation Extraction with Masked Language Models NSTL国家科技图书文献中心

Riley Capshaw | Eva Blomqvist - 《Knowledge Engineering and Knowledge Management》 - International Conference on Knowledge Engineering and Knowledge Management - 2025, - 399～415 - 共17页

摘要： documents in order to facilitate relation* extraction (RE* | Knowledge graphs (KGs) and their related | ontologies constitute a key component in modern knowledge | -based systems. However, hand-crafting these is not | scalable, particularly due to the rate at which knowledge

关键词： Knowledge graphs | Masked language models | Machine reading | Entity embedding | Document-level relation extraction

6. Link prediction for knowledge graphs based on extended relational graph attention networks NSTL国家科技图书文献中心

Zhanyue Cao | Chao Luo - 《Expert Systems with Application》 - 2025,259(Jan.) - 125260.1～125260.12 - 共12页

摘要： embeddings. Secondly, a novel entity and relation embedding | article, an entity-relation-level graph attention | Limited by the sufficiency and timeliness of | information obtained, the connections among entities of | knowledge graphs need to be updated continuously

关键词： Knowledge graphs | Link prediction | Attention mechanism | Knowledge discovery

7. Expressiveness Analysis and Enhancing Framework for Geometric Knowledge Graph Embedding Models NSTL国家科技图书文献中心

Tengwei Song | Long Yin ... - 《IEEE Transactions on Knowledge and Data Engineering》 - 2025,37(1) - 306～318 - 共13页

摘要： embedding models can represent relation patterns. In this | Existing geometric knowledge graph embedding | different relation* patterns, which aims to enhance the* | relation patterns by quantifying the size of the solution | on geometric knowledge graph embedding* models by*

关键词： Analytical models | Data models | Tail | Knowledge graphs | Vectors | Tensors | Predictive models | Semantics | Optimization | Numerical models

8. Dual Context Representation Learning Framework for Entity Alignment NSTL国家科技图书文献中心

Bo Cheng | Jia Zhu ... - 《Big Data Mining and Analytics》 - 2025,8(2) - 346～363 - 共18页

摘要： embedding module introduces relation information to more | accurately aggregate neighbor context. The relation-level | embedding module utilizes neighbor context to enhance | relation-level embeddings. To eliminate semantic gaps | between neighbor-level and relation-level embeddings

关键词： Representation learning | Adaptation models | Aggregates | Semantics | Knowledge graphs | Big Data | Benchmark testing | Data mining

9. TGformer: A Graph Transformer Framework for Knowledge Graph Embedding NSTL国家科技图书文献中心

Fobo Shi | Duantengchuan Li ... - 《IEEE Transactions on Knowledge and Data Engineering》 - 2025,37(1) - 526～541 - 共16页

摘要：Knowledge graph embedding* is efficient method* | embedding of missing entities by a single triple only | unable to discern valuable entity (relation | knowledge graph embedding* (TGformer). It is the first to* | each predicted triplet, which models the relation

关键词： Knowledge graphs | Transformers | Predictive models | Context modeling | Semantics | Tensors | Periodic structures | Graph neural networks | Data models | Parallel processing

10. Enhancing Embedding and Hierarchical Reward Shaping for Multi-Hop Reasoning with Reinforcement Learning NSTL国家科技图书文献中心

Heng Li | Jinhui Wei ... - 《Advanced Data Mining and Applications,Part II》 - International Conference on Advanced Data Mining and Applications - 2025, - 414～429 - 共16页

摘要： reasoning ability by decomposing relation-entity pairs for | consists of the Enhancing Embedding* mechanism and the* | entities. The enhancing embedding* mechanism effectively* | reasoning requirements of the relation* layer and entity* | designs a new relation* layer reward to enhance the*

摘要：. In this paper, we propose a novel lexical relation | embedding approach grounded in hierarchical contrastive | Understanding the lexical relationships | between word pairs is paramount for advancing | applications in natural language processing. However

关键词： Lexical relation | Contrast learning | Prompt learning

摘要： exploit the rich semantic information in relation* labels* | as relation* prior knowledge, which can provide* | understand entity relations, classify relation* labels, and* | enhance the accuracy of joint entity and relation | embedding, named AttRel. Specifically, a novel single

关键词： Joint extraction | Attention mechanisms | Relation embedding

摘要： embedding-based OM approaches, GATHER excels by seamlessly | embedding matcher. Extensive experiments across multiple | Ontology matching (OM) is one of the most | challenging problems in the Semantic Web. Despite | significant progress over the past few decades, evidenced by

关键词： Ontology matching | Graph transformer | Relational graph transformer | Relation embedding generation

摘要： overcome this limitation, we developed a Spatial Relation | -based Knowledge Graph Embedding* framework, SR-KGE* | relation terms among distinct geoentities. This method | diversity of natural language expressions in the embedding | performance in spatial relation* inference compared to*

关键词： Spatial relation | natural language | knowledge graph embedding | joint training

摘要： documents in order to facilitate relation* extraction (RE* | Knowledge graphs (KGs) and their related | ontologies constitute a key component in modern knowledge | -based systems. However, hand-crafting these is not | scalable, particularly due to the rate at which knowledge

关键词： Knowledge graphs | Masked language models | Machine reading | Entity embedding | Document-level relation extraction

摘要： embeddings. Secondly, a novel entity and relation embedding | article, an entity-relation-level graph attention | Limited by the sufficiency and timeliness of | information obtained, the connections among entities of | knowledge graphs need to be updated continuously

关键词： Knowledge graphs | Link prediction | Attention mechanism | Knowledge discovery

摘要： embedding models can represent relation patterns. In this | Existing geometric knowledge graph embedding | different relation* patterns, which aims to enhance the* | relation patterns by quantifying the size of the solution | on geometric knowledge graph embedding* models by*

关键词： Analytical models | Data models | Tail | Knowledge graphs | Vectors | Tensors | Predictive models | Semantics | Optimization | Numerical models

摘要： embedding module introduces relation information to more | accurately aggregate neighbor context. The relation-level | embedding module utilizes neighbor context to enhance | relation-level embeddings. To eliminate semantic gaps | between neighbor-level and relation-level embeddings

关键词： Representation learning | Adaptation models | Aggregates | Semantics | Knowledge graphs | Big Data | Benchmark testing | Data mining

摘要：Knowledge graph embedding* is efficient method* | embedding of missing entities by a single triple only | unable to discern valuable entity (relation | knowledge graph embedding* (TGformer). It is the first to* | each predicted triplet, which models the relation

关键词： Knowledge graphs | Transformers | Predictive models | Context modeling | Semantics | Tensors | Periodic structures | Graph neural networks | Data models | Parallel processing

关键词： Knowledge graph embedding | Reward shaping | Multi-Hop reasoning | Reinforcement learning

4008-161-200 800-990-8900

国家科技图书文献中心

摘要：. In this paper, we propose a novel lexical relation | embedding approach grounded in hierarchical contrastive | Understanding the lexical relationships | between word pairs is paramount for advancing | applications in natural language processing. However

关键词： Lexical relation | Contrast learning | Prompt learning

摘要： exploit the rich semantic information in relation labels | as relation prior knowledge, which can provide | understand entity relations, classify relation labels, and | enhance the accuracy of joint entity and relation | embedding, named AttRel. Specifically, a novel single

关键词： Joint extraction | Attention mechanisms | Relation embedding

摘要： embedding-based OM approaches, GATHER excels by seamlessly | embedding matcher. Extensive experiments across multiple | Ontology matching (OM) is one of the most | challenging problems in the Semantic Web. Despite | significant progress over the past few decades, evidenced by

关键词： Ontology matching | Graph transformer | Relational graph transformer | Relation embedding generation

摘要： overcome this limitation, we developed a Spatial Relation | -based Knowledge Graph Embedding framework, SR-KGE | relation terms among distinct geoentities. This method | diversity of natural language expressions in the embedding | performance in spatial relation inference compared to

关键词： Spatial relation | natural language | knowledge graph embedding | joint training

摘要： documents in order to facilitate relation extraction (RE | Knowledge graphs (KGs) and their related | ontologies constitute a key component in modern knowledge | -based systems. However, hand-crafting these is not | scalable, particularly due to the rate at which knowledge

关键词： Knowledge graphs | Masked language models | Machine reading | Entity embedding | Document-level relation extraction

摘要： embeddings. Secondly, a novel entity and relation embedding | article, an entity-relation-level graph attention | Limited by the sufficiency and timeliness of | information obtained, the connections among entities of | knowledge graphs need to be updated continuously

关键词： Knowledge graphs | Link prediction | Attention mechanism | Knowledge discovery

摘要： embedding models can represent relation patterns. In this | Existing geometric knowledge graph embedding | different relation patterns, which aims to enhance the | relation patterns by quantifying the size of the solution | on geometric knowledge graph embedding models by

关键词： Analytical models | Data models | Tail | Knowledge graphs | Vectors | Tensors | Predictive models | Semantics | Optimization | Numerical models

摘要： embedding module introduces relation information to more | accurately aggregate neighbor context. The relation-level | embedding module utilizes neighbor context to enhance | relation-level embeddings. To eliminate semantic gaps | between neighbor-level and relation-level embeddings

关键词： Representation learning | Adaptation models | Aggregates | Semantics | Knowledge graphs | Big Data | Benchmark testing | Data mining

摘要：Knowledge graph embedding is efficient method | embedding of missing entities by a single triple only | unable to discern valuable entity (relation | knowledge graph embedding (TGformer). It is the first to | each predicted triplet, which models the relation

关键词： Knowledge graphs | Transformers | Predictive models | Context modeling | Semantics | Tensors | Periodic structures | Graph neural networks | Data models | Parallel processing

摘要： reasoning ability by decomposing relation-entity pairs for | consists of the Enhancing Embedding mechanism and the | entities. The enhancing embedding mechanism effectively | reasoning requirements of the relation layer and entity | designs a new relation layer reward to enhance the

关键词： Knowledge graph embedding | Reward shaping | Multi-Hop reasoning | Reinforcement learning

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： exploit the rich semantic information in relation* labels* | as relation* prior knowledge, which can provide* | understand entity relations, classify relation* labels, and* | enhance the accuracy of joint entity and relation | embedding, named AttRel. Specifically, a novel single

摘要： overcome this limitation, we developed a Spatial Relation | -based Knowledge Graph Embedding* framework, SR-KGE* | relation terms among distinct geoentities. This method | diversity of natural language expressions in the embedding | performance in spatial relation* inference compared to*

摘要： documents in order to facilitate relation* extraction (RE* | Knowledge graphs (KGs) and their related | ontologies constitute a key component in modern knowledge | -based systems. However, hand-crafting these is not | scalable, particularly due to the rate at which knowledge

摘要： embedding models can represent relation patterns. In this | Existing geometric knowledge graph embedding | different relation* patterns, which aims to enhance the* | relation patterns by quantifying the size of the solution | on geometric knowledge graph embedding* models by*

摘要：Knowledge graph embedding* is efficient method* | embedding of missing entities by a single triple only | unable to discern valuable entity (relation | knowledge graph embedding* (TGformer). It is the first to* | each predicted triplet, which models the relation