TransEdge: Translating Relation-Contextualized Embeddings for Knowledge Graphs

Sun, Zequn; Huang, Junhui; Hu, Wei; Chen, Muchao; Guo, Lingbing; Qu, Yuzhong

doi:10.1007/978-3-030-30793-6_35

Cited by 101 publications

(48 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, if there are additional tasks such as alignment of relations, one might want to use the KG representation based methods since they intrinsically learn both entity and relation representations. Besides, several recent studies[55],[60] demonstrate that the relations can help the alignment of entities. The bootstrapping process is effective, as it can progressively augment the training set and lead to increasingly better alignment results.…”

mentioning

confidence: 99%

An Experimental Study of State-of-the-Art Entity Alignment Approaches

Zhao

Zeng

Tang

et al. 2020

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Entity alignment (EA) finds equivalent entities that are located in different knowledge graphs (KGs), which is an essential step to enhance the quality of KGs, and hence of significance to downstream applications (e.g., question answering and recommendation). Recent years have witnessed a rapid increase of EA approaches, yet the relative performance of them remains unclear, partly due to the incomplete empirical evaluations, as well as the fact that comparisons were carried out under different settings (i.e., datasets, information used as input, etc.). In this paper, we fill in the gap by conducting a comprehensive evaluation and detailed analysis of state-of-the-art EA approaches. We first propose a general EA framework that encompasses all the current methods, and then group existing methods into three major categories. Next, we judiciously evaluate these solutions on a wide range of use cases, based on their effectiveness, efficiency and robustness. Finally, we construct a new EA dataset to mirror the real-life challenges of alignment, which were largely overlooked by existing literature. This study strives to provide a clear picture of the strengths and weaknesses of current EA approaches, so as to inspire quality follow-up research. ! 1. As where we are standing, EA can be deemed as a special case of entity resolution (ER), which recalls a pile of literature (to be discussed in Section 2.2). Thus, some ER methods (with minor adaptation to handle EA) are also involved in this study to ensure the comprehensiveness of the research.this article, we provide an empirical evaluation of state-of-the-art EA approaches with the following features: (1) Fair comparison within and across categories. Almost all recent studies [5], [24], [38], [55], [60], [61], [62], [63],[67] are confined to comparing with only a subset of methods. In addition, different approaches follow different settings: some merely use the KG structure for alignment, while others also utilize additional information; some align KGs in one pass, while others employ an iterative (re-)training strategy. Although a direct comparison of these methods, as reported in the literature, demonstrates the overall effectiveness of the solutions, a more preferable and fairer practice would be to group these methods into categories and then compare the results both within and across categories.In this study, we include most state-of-the-art methods for lateral comparison, including those very recent efforts that have not yet been compared with others before. By dividing them into three groups and conducting detailed analysis on both intraand inter-group evaluations, we are able to better position these approaches and assess their effectiveness.(2) Comprehensive evaluation on representative datasets. To evaluate the performance of EA systems, several datasets have been constructed, which can be broadly categorized into cross-lingual benchmarks, represented by DBP15K [53], and mono-lingual benchmarks, represented by DWY100K [54]. A very recent study [24] points out th...

show abstract

mentioning

confidence: 99%

An Experimental Study of State-of-the-Art Entity Alignment Approaches

Zhao

Zeng

Tang

et al. 2020

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…The inference phase by default also adopts CSLS as the distance measure, which is consistent with the default setting of recent works (Sun et al, 2019b.…”

Section: Alignment Learningmentioning

confidence: 83%

“…This shows CSLS's ability to handle hubness and isolation is also important for similarity inference in the dense embedding space for the metric words and entities. Hence, this metric is also recommended by recent work (Sun et al, , 2019b. In addition, if we introduce additional 5k seed lexicon (with only word alignment information, not including any entity alignment) provided by Conneau et al (2018) for each language pair, it leads to additional improvement of 1.5-2.2% in H @1.…”

Section: Ablation Studymentioning

confidence: 98%

Cross-lingual Entity Alignment with Incidental Supervision

Chen

Shi

Zhou³

et al. 2021

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

Self Cite

View full text Add to dashboard Cite

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 an incidentally supervised model, JEANS , which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment with incidental supervision signals from text. JEANS first deploys an entity grounding process to combine each KG with the monolingual text corpus. Then, two learning processes are conducted: (i) an embedding learning process to encode the KG and text of each language in one embedding space, and (ii) a selflearning based alignment learning process to iteratively induce the matching of entities and that of lexemes between embeddings. Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision, and significantly outperforms state-of-the-art methods that solely rely on internal information of KGs. 1

show abstract

“…Nevertheless, if there are additional tasks such as alignment of relations, one might want to use the KG representation based methods since they intrinsically learn both entity and relation representations. Besides, several recent studies [23,26] demonstrate that the relations can help the alignment of entities. -The trade-off in bootstrapping.…”

Section: Guidelines For Practitionersmentioning

confidence: 99%

Towards Knowledge Graphs Federations: Issues and Technologies

Zhao

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

In recent decades, knowledge graph plays an increasingly significant role in intelligent information services. However, for some domains, knowledge graphs are constructed for special purposes and disconnected with each other, which fails to take advantage of knowledge from different knowledge graphs. To this end, we are motivated to propose the concept of knowledge graph federation. In this keynote, we first discuss the issues about knowledge graph federation, and then we introduce two technologies of automatic knowledge graph construction, i.e., relation extraction and entity alignment. The issues in this keynote will provide guidelines for the development of knowledge graph technology.

show abstract

TransEdge: Translating Relation-Contextualized Embeddings for Knowledge Graphs

Cited by 101 publications

References 26 publications

An Experimental Study of State-of-the-Art Entity Alignment Approaches

An Experimental Study of State-of-the-Art Entity Alignment Approaches

Cross-lingual Entity Alignment with Incidental Supervision

Towards Knowledge Graphs Federations: Issues and Technologies

Contact Info

Product

Resources

About