Challenge: Entity alignment aims at integrating complementary knowledge graphs (KGs) from different sources or languages.
Approach: They propose a semi-supervised entity alignment method by joint Knowledge Embedding model and Cross-Graph model to make better use of seed alignments to propagate over the entire graphs with KG-based constraints.
Outcome: The proposed method can make better use of seed alignments to propagate over entire graphs with KG-based constraints.

Similar Papers

Jointly Learning Entity and Relation Representations for Entity Alignment (D19-1)

Copied to clipboard

Challenge: Entity alignment is a viable method for integrating heterogeneous knowledge among different knowledge graphs (KGs).
Approach: They propose a Graph Convolutional Network-based framework for learning relation representations by embedding relation seeds into entities and incorporating relation approximation into entities to iteratively improve alignment.
Outcome: The proposed approach outperforms state-of-the-art methods on three real-world cross-lingual datasets.
Knowledge Graph Alignment with Entity-Pair Embedding (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for Knowledge Graph (KG) alignment are not satisfactory.
Approach: They propose a method that directly learns embeddings of entity-pairs for KG alignment.
Outcome: The proposed approach can achieve state-of-the-art on five real-world datasets.
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network (P19-1)

Copied to clipboard

Challenge: Existing approaches to cross-lingual knowledge graph (KG) alignment rely on entity embeddings derived from monolingual KG structural information.
Approach: They propose a topic entity graph to represent entities with contextual information in KGs.
Outcome: The proposed model outperforms state-of-the-art methods by a large margin.
Modeling Multi-mapping Relations for Precise Cross-lingual Entity Alignment (D19-1)

Copied to clipboard

Challenge: Entity alignment aims to find entities in different knowledge graphs (KGs) that refer to the same real-world object.
Approach: They propose to use dot product-based functions to define dot products over embeddings to better capture semantics of 1-N, N-1 and N-N relations.
Outcome: The proposed framework outperforms existing methods on multilingual datasets.
Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks (D18-1)

Copied to clipboard

Challenge: Existing approaches to align multilingual knowledge graphs with counterparts in different languages are not effective.
Approach: They propose a novel approach for cross-lingual KG alignment via graph convolutional networks . they train GCNs to embed entities of each language into a unified vector space .
Outcome: The proposed approach gets the best performance on real multilingual KGs compared with other embedding-based approaches.
OntoEA: Ontology-guided Entity Alignment via Joint Knowledge Graph Embedding (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for aligning knowledge graph entities ignore the ontology which contains critical meta information such as classes and membership relationships with entities.
Approach: They propose an ontology-guided method where KGs and ontologies are jointly embedded.
Outcome: Extensive experiments on seven public and industrial benchmarks show the ontology-guided method performs well and is cost-effective.
TranS: Transition-based Knowledge Graph Embedding with Synthetic Relation Representation (2022.findings-emnlp)

Copied to clipboard

Challenge: Knowledge graph embedding (KGE) is a computational approach to learn continuous vector representations of relations and entities in knowledge graphs.
Approach: They propose a transition-based method to learn continuous vector representations of relations and entities in knowledge graph (KG) it replaces a single relation vector in the relation part with a synthetic relation representation with entity-relation interactions to solve these problems.
Outcome: The proposed method achieves state-of-the-art on a large knowledge graph dataset.
A Contextual Alignment Enhanced Cross Graph Attention Network for Cross-lingual Entity Alignment (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for cross-lingual entity alignment ignore useful pre-aligned links between two KGs.
Approach: They propose a novel method that jointly learns embeddings in different KGs by propagating cross-KG information through pre-aligned seed alignments.
Outcome: The proposed method achieves remarkable performance gains on three benchmark cross-lingual entity alignment datasets.
Jointprop: Joint Semi-supervised Learning for Entity and Relation Extraction with Heterogeneous Graph-based Propagation (2023.acl-long)

Copied to clipboard

Challenge: Named Entity Recognition and Relation Extraction are two crucial tasks in Information Extraction.
Approach: They propose a framework for joint semi-supervised entity and relation extraction that captures the global structure information between tasks and exploits interactions within unlabeled data.
Outcome: The proposed framework outperforms state-of-the-art semi-supervised approaches on NER and RE tasks.
RHGN: Relation-gated Heterogeneous Graph Network for Entity Alignment in Knowledge Graphs (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for entity alignment fail to account for heterogeneity among KGs and distinction between KG entities and relations.
Approach: They propose a Relation-gated Heterogeneous Graph Network (RHGN) that uses a relation-gate based convolutional layer to distinguish relations and entities in the KG.
Outcome: Extensive experiments on four datasets show that the proposed method is superior to state-of-the-art methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations