• Corpus ID: 218470538

Cross-lingual Entity Alignment for Knowledge Graphs with Incidental Supervision from Free Text

@article{Chen2020CrosslingualEA,
  title={Cross-lingual Entity Alignment for Knowledge Graphs with Incidental Supervision from Free Text},
  author={Muhao Chen and Weijia Shi and Ben Zhou and Dan Roth},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.00171}
}
Much research effort has been put to multilingual knowledge graph (KG) embedding methods to address the entity alignment task, which seeks to match entities in different languagespecific KGs that refer to the same real-world object. Such methods are often hindered by the insufficiency of seed alignment provided between KGs. Therefore, we propose a new model, JEANS , which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment… 

Figures and Tables from this paper

Knowledge Acquisition with Transferable and Scalable Representation Learning
TLDR
My goal, in the long term, is to leverage unified methodologies to help machines understand the relations of lexemes, entities and concepts in human languages as well as apprehend the interactions of objects in nature.
Knowledge Acquisition with Transferable and Robust Representation Learning
TLDR
My goal, in the long term, is to leverage unified methodologies to help machines understand the relations of lexemes, entities and concepts in human languages as well as the interactions of objects in nature.

References

SHOWING 1-10 OF 93 REFERENCES
Co-training Embeddings of Knowledge Graphs and Entity Descriptions for Cross-lingual Entity Alignment
TLDR
This paper introduces an embedding-based approach which leverages a weakly aligned multilingual KG for semi-supervised cross-lingual learning using entity descriptions and shows that the performance of the proposed approach on the entity alignment task improves at each iteration of co-training, and eventually reaches a stage at which it significantly surpasses previous approaches.
Cross-lingual Knowledge Graph Alignment via Graph Convolutional Networks
TLDR
This paper proposes a novel approach for cross-lingual KG alignment via graph convolutional networks (GCNs) given a set of pre-aligned entities, and trains GCNs to embed entities of each language into a unified vector space.
Semi-supervised Entity Alignment via Joint Knowledge Embedding Model and Cross-graph Model
TLDR
This paper proposes a semi-supervised entity alignment method by joint Knowledge Embedding model and Cross-Graph model (KECG), which can make better use of seed alignments to propagate over the entire graphs with KG-based constraints.
Modeling Multi-mapping Relations for Precise Cross-lingual Entity Alignment
TLDR
Experimental results show that this approach significantly outperforms many other embedding-based approaches with state-of-the-art performance and proposes a weighted negative sampling strategy to generate valuable negative samples during training and regard prediction as a bidirectional problem in the end.
Cross-Lingual Entity Alignment via Joint Attribute-Preserving Embedding
TLDR
The experimental results on real-world datasets show that this approach significantly outperforms the state-of-the-art embedding approaches for cross-lingual entity alignment and could be complemented with methods based on machine translation.
Aligning Cross-Lingual Entities with Multi-Aspect Information
TLDR
This work investigates embedding-based approaches to encode entities from multilingual KGs into the same vector space, where equivalent entities are close to each other, and applies graph convolutional networks to combine multi-aspect information of entities to learn entity embeddings.
Jointly Learning Entity and Relation Representations for Entity Alignment
TLDR
This paper presents a novel joint learning framework for entity alignment that is a Graph Convolutional Network (GCN) based framework for learning both entity and relation representations and incorporates the relation approximation into entities to iteratively learn better representations for both.
Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment
TLDR
MTransE, a translation-based model for multilingual knowledge graph embeddings, is proposed to provide a simple and automated solution to achieve cross-lingual knowledge alignment and explore how MTransE preserves the key properties of its monolingual counterpart.
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
TLDR
A novel Relation-aware Dual-Graph Convolutional Network is proposed to incorporate relation information via attentive interactions between the knowledge graph and its dual relation counterpart, and further capture neighboring structures to learn better entity representations.
COTSAE: CO-Training of Structure and Attribute Embeddings for Entity Alignment
TLDR
This work proposes COTSAE that combines the structure and attribute information of entities by co-training two embedding learning components, respectively, and proposes a joint attention method in the model to learn the attentions of attribute types and values cooperatively.
...
...