34,283 Hits in 8.2 sec

A Review of Relational Machine Learning for Knowledge Graphs

Maximilian Nickel, Kevin Murphy, Volker Tresp, Evgeniy Gabrilovich
2016 Proceedings of the IEEE  
Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data.  ...  Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web.  ...  However, since links in the graph reveal the occupations of the persons, a relational approach can perform the correct matching. a relational model for large-scale knowledge graphs should scale at most  ... 
doi:10.1109/jproc.2015.2483592 fatcat:uk6xvh5xljgf7aytfadzwzncsi

Context-aware Deep Model for Entity Recommendation in Search Engine at Alibaba [article]

Qianghuai Jia, Ningyu Zhang, Nengwei Hua
2019 arXiv   pre-print
In order to better model the semantics of queries and entities, we learn the representation of queries and entities jointly with attentive deep neural networks.  ...  Entity recommendation, providing search users with an improved experience via assisting them in finding related entities for a given query, has become an indispensable feature of today's search engines  ...  We also thank the anonymous reviewers for their valuable comments and suggestions that help improve the quality of this manuscript.  ... 
arXiv:1909.04493v1 fatcat:eg7pou6l55ajpddguwp4n4lngi

Knowledge Graph informed Fake News Classification via Heterogeneous Representation Ensembles [article]

Boshko Koloski and Timen Stepišnik-Perdih and Marko Robnik-Šikonja and Senja Pollak and Blaž Škrlj
2021 arXiv   pre-print
Furthermore, when combined with existing, contextual representations, knowledge graph-based document representations can achieve state-of-the-art performance.  ...  To our knowledge this is the first larger-scale evaluation of how knowledge graph-based representations can be systematically incorporated into the process of fake news classification.  ...  Substantial advancements were made in this direction in the last years, ranging from large-scale curated knowledge graphs that are freely accessible to contextual language models capable of differentiating  ... 
arXiv:2110.10457v1 fatcat:pevnzvabgvcxpkoxpqxrqvsmsq

Multi-modal Entity Alignment in Hyperbolic Space [article]

Hao Guo, Jiuyang Tang, Weixin Zeng, Xiang Zhao, Li Liu
2021 arXiv   pre-print
We first adopt the Hyperbolic Graph Convolutional Networks (HGCNs) to learn structural representations of entities.  ...  To this end, although existing entity alignment approaches could be adopted, they operate in the Euclidean space, and the resulting Euclidean entity representations can lead to large distortion of KG's  ...  Nevertheless, all of these methods learn entity representations in the Euclidean space, which leads to a large distortion when embedding real-world graphs with scale-free or hierarchical structure [8,  ... 
arXiv:2106.03619v1 fatcat:wpu3tfhl4jbonmwq5nefjyiwli

Multi-source knowledge fusion: a survey

Xiaojuan Zhao, Yan Jia, Aiping Li, Rong Jiang, Yichen Song
2020 World wide web (Bussum)  
On this basis, the challenges and future research directions of multisource knowledge fusion in a large-scale knowledge base environment are discussed.  ...  promote the construction of domain knowledge graphs (KGs), and bring enormous social and economic benefits.  ...  To view a copy of this licence, visit  ... 
doi:10.1007/s11280-020-00811-0 fatcat:ef5j2sna6fai7k2455yihrrfuq

A comprehensive survey of entity alignment for knowledge graphs

Kaisheng Zeng, Chengjiang Li, Lei Hou, Juanzi Li, Ling Feng
2021 AI Open  
This paper investigated almost all the latest knowledge graph representations learning and entity alignment methods and summarized their core technologies and features from different aspects.  ...  A B S T R A C T Knowledge Graphs (KGs), as a structured human knowledge, manage data in an ease-of-store, recognizable, and understandable way for machines and provide a rich knowledge base for different  ...  Knowledge graph representation learning methods The knowledge graph representation learning (RL) method is the cornerstone of those entity alignment methods based on representation learning.  ... 
doi:10.1016/j.aiopen.2021.02.002 fatcat:mj2ens2perb5jn5koxdvjmryii

LinkNBed: Multi-Graph Representation Learning with Entity Linkage

Rakshit Trivedi, Bunyamin Sisman, Xin Luna Dong, Christos Faloutsos, Jun Ma, Hongyuan Zha
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
This has given rise to the construction of numerous large scale but incomplete knowledge graphs encoding information extracted from various resources.  ...  To this end, we propose LinkNBed, a deep relational learning framework that learns entity and relationship representations across multiple graphs.  ...  This has led to the increased efforts in constructing numerous large-scale Knowledge Bases (e.g.  ... 
doi:10.18653/v1/p18-1024 dblp:conf/acl/FaloutsosTSDMZ18 fatcat:2jbo23d3d5benelgik2byae3ni

A Survey on Neural-symbolic Systems [article]

Dongran Yu, Bo Yang, Dayou Liu, Hui Wang
2021 arXiv   pre-print
Combining the fast computation ability of neural systems and the powerful expression ability of symbolic systems, neural-symbolic systems can perform effective learning and reasoning in multi-domain tasks  ...  This paper surveys the latest research in neural-symbolic systems along four dimensions: the necessity of combination, technical challenges, methods, and applications.  ...  target class to help the model learn more transfer features and achieve large-scale few-shot learning tasks.  ... 
arXiv:2111.08164v1 fatcat:bc33afiitnb73bmjtrfbdgkwpy

CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding [article]

Xiou Ge, Yun-Cheng Wang, Bin Wang, C.-C. Jay Kuo
2021 arXiv   pre-print
Entity type prediction is an important problem in knowledge graph (KG) research. A new KG entity type prediction method, named CORE (COmplex space Regression and Embedding), is proposed in this work.  ...  Experiments show that CORE outperforms benchmarking methods on representative KG entity type inference datasets. Strengths and weaknesses of various entity type prediction methods are analyzed.  ...  Autoeter: Automated entity type representation for knowledge graph embedding.  ... 
arXiv:2112.10067v1 fatcat:7ehs7mqagbcgxcaq5jilnsdkcq

Joint Representation Learning of Text and Knowledge for Knowledge Graph Completion [article]

Xu Han, Zhiyuan Liu, Maosong Sun
2016 arXiv   pre-print
Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately.  ...  In this model, both entity and relation embeddings are learned by taking knowledge graph and plain text into consideration.  ...  Typical large-scale knowledge graphs are usually far from complete. The task of knowledge graph completion aims to enrich KGs with novel facts.  ... 
arXiv:1611.04125v1 fatcat:eb2tchisbbbqvjvw3dl2jx7mh4

A Survey of Knowledge Enhanced Pre-trained Models [article]

Jian Yang, Gang Xiao, Yulong Shen, Wei Jiang, Xinyu Hu, Ying Zhang, Jinghui Peng
2022 arXiv   pre-print
Pre-trained models learn informative representations on large-scale training data through a self-supervised or supervised learning method, which has achieved promising performance in natural language processing  ...  In this survey, we provide a comprehensive overview of KEPTMs in NLP and CV. We first introduce the progress of pre-trained models and knowledge representation learning.  ...  Deep learning can fully leverage large-scale data by virtue of distributed representation and hierarchical structure generalization of neural networks.  ... 
arXiv:2110.00269v3 fatcat:b2g3ezuplvftfp7zlehvogd44m

Jointly Embedding Relations and Mentions for Knowledge Population [article]

Miao Fan, Kai Cao, Yifan He, Ralph Grishman
2015 arXiv   pre-print
The proposed model simultaneously learns low-dimensional vector representations for both triplets in knowledge repositories and the mentions of relations in free texts, so that we can leverage the evidence  ...  This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference.  ...  This paper is dedicated to all the members of the Proteus Project.  ... 
arXiv:1504.01683v4 fatcat:jn5q52rj6fdxrkbmn6npt5jf7q

Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model

Chengjiang Li, Yixin Cao, Lei Hou, Jiaxin Shi, Juanzi Li, Tat-Seng Chua
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Specifically, as for the knowledge embedding model, we utilize TransE to implicitly complete two KGs towards consistency and learn relational constraints between entities.  ...  Entity alignment aims at integrating complementary knowledge graphs (KGs) from different sources or languages, which may benefit many knowledge-driven applications.  ...  structural knowledge via shared parame-ters.  ... 
doi:10.18653/v1/d19-1274 dblp:conf/emnlp/LiCHSLC19 fatcat:w44wyk4kb5bqvoxk53cr6kqbka

World Knowledge Representation [chapter]

Zhiyuan Liu, Yankai Lin, Maosong Sun
2020 Representation Learning for Natural Language Processing  
World knowledge representation aims to represent entities and relations in the knowledge graph in low-dimensional semantic space, which have been widely used in large knowledge-driven tasks.  ...  ., Representation Learning for Natural Language Processing, 163 164 7 World Knowledge Representation World Knowledge Graphs In ancient times, knowledge was stored  ...  Knowledge-Guided Information Retrieval The emergence of large-scale knowledge graphs has motivated the development of entity-oriented search, which utilizes knowledge graphs to improve search engines.  ... 
doi:10.1007/978-981-15-5573-2_7 fatcat:nzn3gdsjozh4jfzqu6ux345uci

MRP2Rec: Exploring Multiple-step Relation Path Semantics for Knowledge Graph-Based Recommendations

Ting Wang, Daqian Shi, Zhaodan Wang, Shuai Xu, Hao Xu
2020 IEEE Access  
For integrating large-scale heterogeneous data, collaborative filtering with knowledge graph (CFKG) [19] extends CF by proposing a representation learning approach that embeds heterogeneous entities  ...  CoFM [20] combines the recommendation task and knowledge graph learning task by sharing parameters of aligned items and entities.  ... 
doi:10.1109/access.2020.3011279 fatcat:tbztgj6qljgsnanmmpubvufcte
« Previous Showing results 1 — 15 out of 34,283 results