Special Issue on “Extraction and Evaluation of Knowledge Entities from Scientific Documents”

Guest Editors

Chengzhi Zhang, Nanjing University of Science and Technology, China

Philipp Mayr, GESIS - Leibniz-Institute for the Social Sciences department Knowledge Technologies for the Social Sciences (WTS), Germany

Wei Lu, Wuhan University, China

Yi Zhang, University of Technology Sydney (UTS), Australia

1. About the special issue

A knowledge entity is a relatively independent and integral knowledge module in a special discipline or a research domain (Chang & Zheng, 2007). As a crucial medium for knowledge transmission, scientific documents that contain a large number of knowledge entities attract the attention of scholars (Ding et. al, 2013). In scientific documents, knowledge entities refer to the knowledge mentioned or cited by authors, such as algorithms, models, theories, datasets and software, which reflect the various resources used by the authors in solving problems (Hou et. al, 2019; Arthur et. al, 2020). Extracting knowledge entities from scientific documents in an accurate and comprehensive way becomes a significant topic. We may recommend documents related to a given knowledge entity (e.g., the long short-term memory model) for scholars, especially for beginners in a research field. As an example, Defense Advanced Research Projects Agency of the United States (DARPA US) has recently launched the Automating Scientific Knowledge Extraction (ASKE) project, which aims to develop next-generation applications of artificial intelligence.

At present, scholars have used knowledge entities to construct general knowledge graphs (e.g., Google Knowledge Graph) and domain knowledge graphs (e.g., GeoNames). Data sources for these approaches include text (news, policy files, emails, etc.) and multimedia (videos, images, etc.) data. Open Academic Graph (OAG) is a large academic knowledge graph and includes about 700 million entities and 2 billion relationships. However, entities in OAG are mainly metadata of academic papers, not including knowledge entities. It is an interesting and challenging work about extraction and evaluation of knowledge entities from scientific documents.

This special issue (SI) is expected to provide scholars, especially early career researchers, with knowledge recommendations and other knowledge entity-based services.

2. Objective and topics

This SI aligns with computer and information science, especially topics in information extraction, text mining, natural language processing, information retrieval and digital libraries. It will also be of importance for all stakeholders in the publication pipeline: implementers, publishers and policymakers.

The SI entitles this cutting-edge and cross-disciplinary direction Extraction and Evaluation of Knowledge Entity, highlighting the development of intelligent methods for identifying knowledge claims in scientific documents and promoting the application of knowledge entities. We invite stimulating research on topics including, but not limited to, methods of knowledge entity extraction and applications of knowledge entity. Specific examples of fields of interest include:

  •       Task and methodology from scientific documents
  •       Model and algorithm extraction from scientific documents
  •       Dataset and evaluation metrics extraction from documents
  •       Software and tool extraction from scientific documents
  •       Construction of a knowledge entity graph and roadmap
  •       Knowledge entity summarization
  •       Relation extraction of knowledge entity
  •       Construction of a knowledge base of knowledge entities
  •       Modeling function of knowledge entity citation
  •       Bibliometrics of knowledge entity
  •       Application of knowledge entity extraction.

3. Important dates

Paper submission: 31 October 2020
Review reports and invitation to submit revised paper: 30 November 2020

Revised paper submission: 15 January 2021 Expected publication: May 2021

4. Submission and review process

Papers should be prepared according to the submission guidelines of JDIS (see http://manu47.magtech.com.cn/Jwk3_jdis/EN/column/column315.shtml). Please submit your manuscript through ScholarOne Submission System (https://mc03.manuscriptcentral.com/jdis) of the journal. When submitting, please select the "Other" article type described as "Special Issue on ‘Extraction and Evaluation of Knowledge Entities from Scientific Documents’". Submitted papers should ideally be no more than 15 pages (including tables, figures, and references) but longer versions can be taken if the content merits.

Papers submitted must not have been submitted to or published in any other journal. All manuscripts will undergo a peer review process. Accepted papers will be freely available online as OPEN ACCESS papers WITHOUT any article processing charges.

Further information

For questions regarding this special issue, please contact the Guest Editors: 
      Chengzhi Zhang (zhangcz@njust.edu.cn), 
      Philipp Mayr (philipp.mayr@gesis.org), 
      Wei Lu (weilu@whu.edu.cn), 
      Yi Zhang (Yi.Zhang@uts.edu.au). 

For technical details on submitting, please contact Ms Ping Meng (mengp@mail.las.ac.cn) .


Arthur Brack, Jennifer D’Souza, Anett Hoppe, Soren Auer, and Ralph Ewerth. (2020). Domain-independent Extraction of Scientific Concepts from Research Articles. arXiv preprint arXiv:2001.03067 

Xiao Chang and Qinghua Zheng. (2007). Knowledge element extraction for knowledge-based learning resources organization. In International Conference on Web-Based Learning. Springer, 102–113. 

Ying Ding, Min Song, Jia Han, Qi Yu, Erjia Yan, Lili Lin, and Tamy Chambers. (2013). Entitymetrics: Measuring the impact of entities. PloS one 8, 8 

Yufang Hou, Charles Jochim, Martin Gleize, Francesca Bonin, and Debasis Ganguly. (2019). Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 5203–5213.