BERT-INT:A BERT-based Interaction Model For Knowledge Graph Alignment

Tang, Xiaobin; Zhang, Jing; Chen, Bo; Yang, Yang; Chen, Hong; Li, Cuiping

doi:10.24963/ijcai.2020/439

Cited by 58 publications

(54 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A more detailed discussion about these methods and the difference from our framework is provided in Section 5. Methods in the third category incorporate the side information to offer a complementing view to the KG structure, including the attributes [10,[26][27][28][29][30], entity descriptions [16,31], and entity names [12,25,[32][33][34][35].…”

Section: Related Workmentioning

confidence: 99%

Toward Entity Alignment in the Open World: An Unsupervised Approach with Confidence Modeling

et al. 2022

View full text Add to dashboard Cite

Entity alignment (EA) aims to discover the equivalent entities in different knowledge graphs (KGs). It is a pivotal step for integrating KGs to increase knowledge coverage and quality. Recent years have witnessed a rapid increase of EA frameworks. However, state-of-the-art solutions tend to rely on labeled data for model training. Additionally, they work under the closed-domain setting and cannot deal with entities that are unmatchable. To address these deficiencies, we offer an unsupervised framework that performs entity alignment in the open world. Specifically, we first mine useful features from the side information of KGs. Then, we devise an unmatchable entity prediction module to filter out unmatchable entities and produce preliminary alignment results. These preliminary results are regarded as the pseudo-labeled data and forwarded to the progressive learning framework to generate structural representations, which are integrated with the side information to provide a more comprehensive view for alignment. Finally, the progressive learning framework gradually improves the quality of structural embeddings and enhances the alignment performance. Furthermore, noticing that the pseudo-labeled data are of various qualities, we introduce the concept of confidence to measure the probability of an entity pair of being true and develop a confidence-based unsupervised EA framework . Our solutions do not require labeled data and can effectively filter out unmatchable entities. Comprehensive experimental evaluations validate the superiority of our proposals .

show abstract

Section: Related Workmentioning

confidence: 99%

Toward Entity Alignment in the Open World: An Unsupervised Approach with Confidence Modeling

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Some leverage semi-supervised learning techniques to resolve the training data insufficiency issue, including self-learning (Sun et al, 2018;Mao et al, 2020) and co-training (Chen et al, 2018). (iii) Another line of research seeks to retrieve auxiliary or indirect supervision signals from profile information or side features of entities, such as entity attributes (Sun et al, 2017;Trisedya et al, 2019;Pei et al, 2019), literals (Wu et al, 2019(Wu et al, , 2020bLiu et al, 2020), free text , pre-trained language models (Yang et al, 2019;Tang et al, 2020) or visual modalities (Liu et al, 2021). Due to the large body of recent advances, we refer readers to a more comprehensive summarization in the survey (Sun et al, 2020c).…”

Section: Entity Alignmentmentioning

confidence: 99%

“…Despite the importance, KGs are usually costly to construct (Paulheim, 2018) and naturally suffer from incompleteness (Galárraga et al, 2017). Hence, merging multiple KGs through entity alignment can lead to mutual enrichment of their knowledge (Chen et al, 2020), and provide downstream applications with more comprehensive knowledge representations (Trivedi et al, 2018;Chen et al, 2020). Entity alignment seeks to discover identical entities in different KGs, such as English entity Thailand and its French counterpart Thaïlande.…”

Section: Introductionmentioning

confidence: 99%

Knowing the No-match: Entity Alignment with Dangling Cases

Sun

Chen

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

This paper studies a new problem setting of entity alignment for knowledge graphs (KGs). Since KGs possess different sets of entities, there could be entities that cannot find alignment across them, leading to the problem of dangling entities. As the first attempt to this problem, we construct a new dataset and design a multi-task learning framework for both entity alignment and dangling entity detection. The framework can opt to abstain from predicting alignment for the detected dangling entities. We propose three techniques for dangling entity detection that are based on the distribution of nearest-neighbor distances, i.e., nearest neighbor classification, marginal ranking and background ranking. After detecting and removing dangling entities, an incorporated entity alignment model in our framework can provide more robust alignment for remaining entities. Comprehensive experiments and analyses demonstrate the effectiveness of our framework. We further discover that the dangling entity detection module can, in turn, improve alignment learning and the final performance. The contributed resource is publicly available to foster further research.

show abstract

“…JEANS (Chen et al, 2021) is distinctive in that it links ('grounds') a text corpus to enities and uses TransE (Bordes et al, 2013) for the KG, skip-grams for the text, with additional alignment constraints as usual. BERT-INT (Tang et al, 2020) is another EA system that combines mBERT-obtained features from entity aliases and text descriptions with soft 1-hop graph neighborhood matching. Except MultiKE, most systems focus on EA, assuming RA is unnecessary, or already accomplished.…”

Section: Kg Alignmentmentioning

confidence: 99%

“…This leads to the problem of ID proliferation. A recent line of research around entity alignment (EA) across KGs in different languages attempts to assign a unique ID to all IDs representing the same entity (Chen et al, 2017;Sun et al, 2017Sun et al, , 2018Cao et al, 2019;Sun et al, 2020;Chen et al, 2021;Tang et al, 2020). A related task is relation alignment (RA), though relatively less attention has been given to this for multilingual KGs.…”

Section: Introductionmentioning

confidence: 99%

Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment

Singh¹,

Jain²,

Mausam³

et al. 2021

Preprint

View full text Add to dashboard Cite

Knowledge Graph Completion (KGC) predicts missing facts in an incomplete Knowledge Graph. Almost all of existing KGC research is applicable to only one KG at a time, and in one language only. However, different language speakers may maintain separate KGs in their language and no individual KG is expected to be complete. Moreover, common entities or relations in these KGs have different surface forms and IDs, leading to ID proliferation. Entity alignment (EA) and relation alignment (RA) tasks resolve this by recognizing pairs of entity (relation) IDs in different KGs that represent the same entity (relation). This can further help prediction of missing facts, since knowledge from one KG is likely to benefit completion of another. High confidence predictions may also add valuable information for the alignment tasks.In response, we study the novel task of jointly training multilingual KGC, relation alignment and entity alignment models. We present ALIGNKGC, which uses some seed alignments to jointly optimize all three of KGC, EA and RA losses. A key component of ALIGN-KGC is an embedding-based soft notion of asymmetric overlap defined on the (subject, object) set signatures of relations -this aids in better predicting relations that are equivalent to or implied by other relations. Extensive experiments with DBPedia in five languages establish the benefits of joint training for all tasks, achieving 10-32 MRR improvements of ALIGNKGC over a strong state-ofthe-art single-KGC system completion model over each monolingual KG . Further, ALIGN-KGC achieves reasonable gains in EA and RA tasks over a vanilla completion model over a KG that combines all facts without alignment, underscoring the value of joint training for these tasks.

show abstract

BERT-INT:A BERT-based Interaction Model For Knowledge Graph Alignment

Cited by 58 publications

References 22 publications

Toward Entity Alignment in the Open World: An Unsupervised Approach with Confidence Modeling

Toward Entity Alignment in the Open World: An Unsupervised Approach with Confidence Modeling

Knowing the No-match: Entity Alignment with Dangling Cases

Multilingual Knowledge Graph Completion with Joint Relation and Entity Alignment

Contact Info

Product

Resources

About