Automatic processing of bibliographic data becomes very important in digital libraries, data science and machine learning due to its importance in keeping pace with the significant increase of published papers every year from one side and to the inherent challenges from the other side. This processing has several aspects including but not limited to I) Automatic extraction of references from PDF documents, II) Building an accurate citation graph, III) Author name disambiguation, etc. Bibliographic data is heterogeneous by nature and occurs in both structured (e.g. citation graph) and unstructured (e.g. publications) formats. Therefore, it requires data science and machine learning techniques to be processed and analysed. The aim of this workshop is to address open challenges in digital libraries and to attract the attention of the research communities to present novel approaches to bibliographic data analysis, processing and understanding. Consequently, we invite the submission of original and high-quality research papers and reports of live demonstrations and prototypes on the following and any related topics:
Author Name Disambiguation (AND) is an open challenging problem and its effects are growing as the number of authors sharing the same names arises significantly. To fill the gap between the challenges of AND caused by the continuous increase of authors sharing the same name from one side and the remarkable advancement of artificial intelligence from the other side, we are also organizing a shared task on Author Name Disambiguation. To this end, we will release two annotated datasets; one for development and one for testing. The workshop invites researchers to submit their results and request those with high accuracy to submit their original research papers, live demonstrations and source codes that tackle this particular problem.
All submissions must be original contributions. If a paper is under review for the main conference or for a different conference, it should be mentioned in the subtitle. In this case, it is the responsibility of the authors to confirm whether they are allowed to resubmit their papers. All papers must not exceed 6 pages and follow the template guidelines of the main conference which can be found here https://www.acm.org/publications/proceedings-template.
Note that this is a non-archival workshop. We accept submissions of paper that are under review to other venues, including KDD'21. However, if your paper is accepted to the main conference, we expect you to withdraw your submission to BiblioDap. We encourage all authors to post their papers to arXiv.
Please, note that we support open peer review and we allow reviewers to disclose their identities and publish their reviews according to the guidelines available at https://open-sci.github.io/review/.
Selected papers will be invited for an extension to be considered in a special issue of Scientometrics journal (Impact factor: 2.770). The review comments of workshop version will be taken into account.