Generating Knowledge Graphs by Employing Natural Language Processing and Machine Learning Techniques within the Scholarly Domain

@article{Dess2020GeneratingKG,
  title={Generating Knowledge Graphs by Employing Natural Language Processing and Machine Learning Techniques within the Scholarly Domain},
  author={Danilo Dess{\'i} and Francesco Osborne and Diego Reforgiato Recupero and D. Buscaldi and Enrico Motta},
  journal={Future Gener. Comput. Syst.},
  year={2020},
  volume={116},
  pages={253-264}
}
View PDF on arXiv
29 Citations
Background Citations
8
Methods Citations
7

Figures and Tables from this paper

29 Citations

Completing Scientific Facts in Knowledge Graphs of Research Concepts

This paper introduces SciCheck, a new triple classification approach for completing scientific statements in knowledge graphs and provides a real-world use case and applies it to the Artificial Intelligence Knowledge Graph (AI-KG).

AI-KG: An Automatically Generated Knowledge Graph of Artificial Intelligence

The Artificial Intelligence Knowledge Graph (AI-KG), a large-scale automatically generated knowledge graph that describes 820K research entities, has been generated by applying an automatic pipeline that extracts entities and relationships using three tools: DyGIE++, Stanford CoreNLP, and the CSO Classifier.

Scholarly knowledge graphs through structuring scholarly communication: a review

This review paper investigates the field of applying machine learning, rule-based learning, and natural language processing tools and approaches to construct SKG and presents the review of knowledge graph utilization and refinement to provide a view of current research efforts.

CS-KG: A Large-Scale Knowledge Graph of Research Entities and Claims in Computer Science

The Computer Science Knowledge Graph (CS-KG) is introduced, a large-scale knowledge graph composed by over 350 M RDF triples describing 41 M statements from 6 .7 M articles about 10 M entities linked by 179 semantic relations that provides a very comprehensive representation of tasks, methods, materials, and metrics in Computer Science.

Taxonomy Enrichment with Text and Graph Vector Representations

This paper addresses the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy with a new method which allows achieving high results on this task with little effort and creates a number of datasets for taxonomy extension for English and Russian.

Scientific Knowledge Graph-driven Research Profiling

A research profiling framework driven by scientific knowledge graphs (SKGs), which aims at achieving the deep fusion and thorough disclosure of scientific resources and domain knowledge, as well as satisfying the needs of researchers for knowledge overview and acquisition in a reasonable period of time using fine-grained and multi-dimensional profiling scenarios.

Detection, Analysis, and Prediction of Research Topics with Scientific Knowledge Graphs

This chapter presents an innovative framework for detecting, analysing, and forecasting research topics based on a large-scale knowledge graph characterising research articles according to the research topics from the Computer Science Ontology.

K-LM: Knowledge Augmenting in Language Models Within the Scholarly Domain

This work provides a Knowledge Language Model (K-LM) to use the Resource Description Framework (RDF) triples directly, extracted from world knowledge bases and introduces heuristic methods to inject domain-specific knowledge in K-LM, leveraging knowledge graphs (KGs).

CSO Classifier 3.0: a scalable unsupervised method for classifying documents in terms of research topics

This new version of the CSO Classifier includes a new component for discarding outlier topics and offers improved scalability, and is evaluated on a gold standard of manually annotated articles, demonstrating a significant improvement over alternative methods.

CSO Classifier 3.0: a scalable unsupervised method for classifying documents in terms of research topics

This new version of the CSO Classifier includes a new component for discarding outlier topics and offers improved scalability, and is evaluated on a gold standard of manually annotated articles, demonstrating a significant improvement over alternative methods.

References

SHOWING 1-10 OF 50 REFERENCES

Mining Scholarly Data for Fine-Grained Knowledge Graph Construction

This paper presents a preliminary approach that uses a set of NLP and Deep Learning methods for extracting entities and relationships from research publications and then integrates them in a KG.

Mining Scholarly Publications for Scientific Knowledge Graph Construction

This paper tackles the challenge of knowledge extraction by employing several state-of-the-art Natural Language Processing and Text Mining tools, describes an approach for integrating entities and relationships generated by these tools, and analyses an automatically generated Knowledge Graph.

Extracting Semantic Relations for Scholarly Knowledge Base Construction

A system to extract semantic relations among entities in scholarly articles by making use of external syntactic patterns and an iterative learner shows that it obtains a 23% improvement in precision over existing web IE tools when they are applied to scholarly documents.

Microsoft Academic Graph: When experts are not enough

The design, schema, and technical and business motivations behind MAG are described and how MAG can be used in analytics, search, and recommendation scenarios are elaborated.

Integrating Knowledge Graphs for Analysing Academia and Industry Dynamics

This short paper introduces the Academia/Industry DynAmics (AIDA) Knowledge Graph, which characterizes 14M papers and 8M patents according to the research topics drawn from the Computer Science Ontology.

OpenIE-based approach for Knowledge Graph construction from text

Towards a Definition of Knowledge Graphs

This work discusses and defines the term knowledge graph, considering its history and diversity in interpretations and use, and proposes a definition of knowledge graphs that serves as basis for discussions on this topic and contributes to a common vision.

Open Research Knowledge Graph: Towards Machine Actionability in Scholarly Communication

Initial steps towards next generation digital libraries and infrastructures that acquire, curate, publish and process scholarly knowledge semantically, in machine readable form leveraging knowledge graphs are presented.

Dr. Inventor Framework: Extracting Structured Information from Scientific Publications

The first version of the Dr. Inventor Framework, a publicly available collection of scientific text mining components useful to prevent or at least mitigate this problem of textual analysis of scientific papers, is presented.

A Survey of Relation Extraction of Knowledge Graphs

The development process of relation extraction is discussed, the characteristics of different relation extraction algorithms are elucidate, the potential research directions in the future are given, and deep learning, reinforcement learning, active learning and transfer learning are discussed.