Scalable Knowledge Graph Construction over Text using Deep Learning based Predicate Mapping

Mehta, Aman; Singhal, Aashay; Karlapalem, Kamalakar

doi:10.1145/3308560.3317708

Cited by 16 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are many off-the-shelf toolkits available, for example, Stanford CoreNLP [12], NLTK [13], and spaCy, which can be used for the NER tasks; Reveb [14], OLLIE [15], and Stanford OpenIE [16] can be used for the information extraction task. There have been multiple pipelines [6], [17] developed as well, consisting of modules targeting different functionalities needed for the KG construction. However, the pre-defined rules of off-the-shelf toolkits are generally tailored to specific domains, such methods are not domainagnostic, and a new set of rules will be needed for a new domain.…”

Section: Related Work a Pipeline-based Methods For Kg Constructionmentioning

confidence: 99%

Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training

Cai¹,

Liao²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Modern supervised learning neural network models require a large amount of manually labeled data, which makes the construction of domain-specific knowledge graphs timeconsuming and labor-intensive. In parallel, although there has been much research on named entity recognition and relation extraction based on distantly supervised learning, constructing a domain-specific knowledge graph from large collections of textual data without manual annotations is still an urgent problem to be solved. In response, we propose an integrated framework for adapting and re-learning knowledge graphs from one coarse domain (biomedical) to a finer-define domain (oncology). In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation. Consequently, no manual data annotation is required to train the model. We introduce a novel iterative training strategy to facilitate the discovery of domainspecific named entities and triples. Experimental results indicate that the proposed framework can perform domain adaptation and construction of knowledge graph efficiently.

show abstract

Section: Related Work a Pipeline-based Methods For Kg Constructionmentioning

confidence: 99%

Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training

Cai¹,

Liao²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The other category of methods [40]- [46] tries to construct knowledge graph by automatically extracting knowledge from unstructured data source such as texts, images, or other media. Among them, [40]- [42] is to extract structured knowledge from domain-related texts to construct domain knowledge graph. However, HDSKG [44] extracts relational triples from Web pages and then uses a pre-trained SVM classifier and domain dictionary to determine the domain relevance of the extracted triples.…”

Section: Construction Of Knowledge Graphmentioning

confidence: 99%

From Vision to Content: Construction of Domain-Specific Multi-Modal Knowledge Graph

et al. 2019

View full text Add to dashboard Cite

Knowledge graphs are usually constructed to describe the various concepts that exist in real world as well as the relationships between them. There are many knowledge graphs in specific fields, but they usually pay more attention on text or structured data, ignoring the image vision information, and cannot play an adequate role in the emerging visualization applications. Aiming at this issue, we design a method that integrates image vision information and text information derived from Wikimedia Commons to construct a domain-specific multi-modal knowledge graph, taking the metallic materials domain as an example to illustrate the method. The text description of each image is regarded as its context semantic to acquire the image's context semantic labels based on the DBpedia resource. Furthermore, we adopt deep neural network model instead of simple visual descriptors to acquire the image's visual semantic labels using the concepts from WordNet. In order to fuse the visual semantic labels and context semantic labels, a path-based concept extension and fusion strategy is proposed based on the conceptual hierarchies of WordNet and DBpedia to obtain the effective extension concepts as well as the links between them, increasing the scale of the knowledge graph and enhancing the correlation between images. The experimental results show that the maximum extension level has a significant impact on the quality of the generated domain knowledge graph, and the best extension level number is respectively determined for both DBpedia and WordNet. In addition, the results of this paper are compared with IMGpedia to further show the effectiveness of the proposed method. INDEX TERMS Knowledge graph, information fusion, multi-modal knowledge, metallic materials knowledge. IV. CONSTRUCTION METHOD OF DOMAIN-SPECIFIC MULTI-MODAL KNOWLEDGE GRAPH A. APPROACH OVERVIEW

show abstract

“…Several quality dimensions that capture multifaceted aspects of KG quality have been discussed, e.g. correctness (Hogan et al , 2021; Gao et al , 2019; Noy et al , 2019; Mishra et al , 2017), coverage (also called comprehensiveness) (Hogan et al , 2021; Noy et al , 2019; Mishra et al , 2017), coherency (Hogan et al , 2021), freshness (Chen et al , 2019; Noy et al , 2019), scalability (Chen et al , 2019; Mehta et al , 2019) and relatedness (Chen et al , 2019). Among all dimensions, correctness, coverage and freshness are the three key determinants of the KG’s quality and usefulness (Noy et al , 2019), whereas relatedness is crucial for RS and Q&A systems (Chen et al , 2019).…”

Section: Introductionmentioning

confidence: 99%

Construction and evaluation of a domain-specific knowledge graph for knowledge discovery

Nguyen

Chen

et al. 2023

IDD

View full text Add to dashboard Cite

Purpose This study aims to evaluate a method of building a biomedical knowledge graph (KG). Design/methodology/approach This research first constructs a COVID-19 KG on the COVID-19 Open Research Data Set, covering information over six categories (i.e. disease, drug, gene, species, therapy and symptom). The construction used open-source tools to extract entities, relations and triples. Then, the COVID-19 KG is evaluated on three data-quality dimensions: correctness, relatedness and comprehensiveness, using a semiautomatic approach. Finally, this study assesses the application of the KG by building a question answering (Q&A) system. Five queries regarding COVID-19 genomes, symptoms, transmissions and therapeutics were submitted to the system and the results were analyzed. Findings With current extraction tools, the quality of the KG is moderate and difficult to improve, unless more efforts are made to improve the tools for entity extraction, relation extraction and others. This study finds that comprehensiveness and relatedness positively correlate with the data size. Furthermore, the results indicate the performances of the Q&A systems built on the larger-scale KGs are better than the smaller ones for most queries, proving the importance of relatedness and comprehensiveness to ensure the usefulness of the KG. Originality/value The KG construction process, data-quality-based and application-based evaluations discussed in this paper provide valuable references for KG researchers and practitioners to build high-quality domain-specific knowledge discovery systems.

show abstract

Scalable Knowledge Graph Construction over Text using Deep Learning based Predicate Mapping

Cited by 16 publications

References 22 publications

Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training

Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training

From Vision to Content: Construction of Domain-Specific Multi-Modal Knowledge Graph

Construction and evaluation of a domain-specific knowledge graph for knowledge discovery

Contact Info

Product

Resources

About