A survey on knowledge graph embeddings with literals: Which model links better literal-ly?

Gesese, Genet Asefa; Biswas, Russa; Alam, Mehwish; Sack, Harald

doi:10.3233/sw-200404

Cited by 40 publications

(23 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, approaches combining textual information with knowledge graph embeddings using language modeling techniques have also been proposed, using techniques such as word2vec and convolutional neural networks [45] or transformer methods [9,43]. [11] shows a survey of approaches which take such literal information into account. It is also one of the few review articles which considers embedding methods from the different research strands.…”

Section: Related Workmentioning

confidence: 99%

“…For node2vec, DeepWalk, and KGlove, we use the standard settings and the code provided by the respective authors. 11,12,13 For KGlove, we use the Inverse Predicate Frequency, which has been reported to work well on many tasks by the original paper [7]. It is noteworthy that the default settings for node2vec and DeepWalk differ in one crucial property.…”

Section: Portisch Et Al / Knowledge Graph Embedding For Data Mining V...mentioning

confidence: 99%

“…The code for the experiments as well as the resulting embeddings can be found at https://github.com/nheist/KBE-for-Data-Mining 11. https://github.com/D2KLab/entity2vec 12 https://github.com/phanein/deepwalk 13 https://github.com/miselico/globalRDFEmbeddingsISWC…”

mentioning

confidence: 99%

See 2 more Smart Citations

Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction – two sides of the same coin?

Portisch

Heist

Paulheim

2022

View full text Add to dashboard Cite

Knowledge Graph Embeddings, i.e., projections of entities and relations to lower dimensional spaces, have been proposed for two purposes: (1) providing an encoding for data mining tasks, and (2) predicting links in a knowledge graph. Both lines of research have been pursued rather in isolation from each other so far, each with their own benchmarks and evaluation methodologies. In this paper, we argue that both tasks are actually related, and we show that the first family of approaches can also be used for the second task and vice versa. In two series of experiments, we provide a comparison of both families of approaches on both tasks, which, to the best of our knowledge, has not been done so far. Furthermore, we discuss the differences in the similarity functions evoked by the different embedding approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Portisch Et Al / Knowledge Graph Embedding For Data Mining V...mentioning

confidence: 99%

See 1 more Smart Citation

Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction – two sides of the same coin?

Portisch

Heist

Paulheim

2022

View full text Add to dashboard Cite

show abstract

“…Leveraging literals in KG is a challenging task [47]. Gesese et al [49] conducted a survey on KGE for multimodal knowledge graphs, in which they covered models such as KBLRN [50], LiteralE [51], and many more. An overview of existing techniques related to multimodality, including temporal and uncertain knowledge graphs, is also conducted in our survey providing readers a comprehensive view on KGC.…”

Section: Related Work and Contributionsmentioning

confidence: 99%

A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges

Garg¹,

Roy²

2022

Preprint

View full text Add to dashboard Cite

In recent years, Knowledge Graph (KG) development has attracted significant researches considering the applications in web search, relation prediction, natural language processing, information retrieval, question answering to name a few. However, often KGs are incomplete due to which Knowledge Graph Completion (KGC) has emerged as a sub-domain of research to automatically track down the missing connections in a KG. Numerous strategies have been suggested to work out the KGC dependent on different representation procedures intended to embed triples into a low-dimensional vector space. Given the difficulties related to KGC, researchers around the world are attempting to comprehend the attributes of the problem statement. This study intends to provide an overview of knowledge bases combined with different challenges and their impacts. We discuss existing KGC approaches, including the state-of-the-art Knowledge Graph Embeddings (KGE), not only on static graphs but also for the latest trends such as multimodal, temporal, and uncertain knowledge graphs. In addition, reinforcement learning techniques are reviewed to model complex queries as a link prediction problem. Subsequently, we explored popular software packages for model training and examine open research challenges that can guide future research.

show abstract

“…24,25 Our experiments with training TransE 26 embeddings on a knowledge graph built from SMG's data led to embeddings that were too poor in quality to be used in a record linkage system, due to the data's 'thinness'small number of properties per record and links between recordsthat the software is designed to overcome. Knowledge graph embeddings which incorporate information from literals 27 may well produce better results on similar knowledge graphs, but at the time of writing there are no mature libraries that can be used to produce any such embeddings.…”

Section: Record Linkage To Wikidatamentioning

confidence: 99%

Heritage connector: A machine learning framework for building linked open data from museum collections

Dutia

Stack

2021

Applied AI Letters

View full text Add to dashboard Cite

As with almost all data, museum collection catalogues are largely unstructured, variable in consistency and overwhelmingly composed of thin records. The form of these catalogues means that the potential for new forms of research, access and scholarly enquiry that range across multiple collections and related datasets remains dormant. In the project Heritage Connector: Transforming text into data to extract meaning and make connections, we are applying a battery of digital techniques to connect similar, identical and related objects within and across collections and other publications. In this article, we describe a framework to create a Linked Open Data knowledge graph from digital museum catalogues, perform record linkage to Wikidata, and add new entities to this graph from textual catalogue record descriptions (information retrieval). We focus on the use of machine learning to create these links at scale with a small amount of labelled data, and models which are small enough to run inference on datasets the size of museum collections on a mid‐range laptop or a small cloud virtual machine. Our method for record linkage against Wikidata achieves 85%+ precision with the Science Museum Group (SMG) collection, and our method for information retrieval is shown to improve NER performance compared with pretrained models on the SMG collection with no labelled training data. We publish open‐source software providing tools to perform these tasks.

show abstract

A survey on knowledge graph embeddings with literals: Which model links better literal-ly?

Cited by 40 publications

References 57 publications

Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction – two sides of the same coin?

Knowledge graph embedding for data mining vs. knowledge graph embedding for link prediction – two sides of the same coin?

A Birds Eye View on Knowledge Graph Embeddings, Software Libraries, Applications and Challenges

Heritage connector: A machine learning framework for building linked open data from museum collections

Contact Info

Product

Resources

About