Rapid Tagging and Reporting for Functional Language Extraction in Scientific Articles
Date
Authors
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Authors
Research Projects
Organizational Units
Journal Issue
Is Version Of
Versions
Series
Department
Abstract
This paper describes the development of a web-based application for tagging scientific articles, in part to create machine learning training datasets for automated functional language identification and extraction (AFLEX). The initial intent for this work was to provide a new member of the ecosystem of tools that facilitate the structured automation of systematic reviews, an area of work that typically requires critical analysis of multiple research studies and provides an exhaustive summary of literature related to a research question. However, the tool’s modular interface allows use across disciplines. A user may upload PDF or text documents and quickly tag selected parts of the document with a customizable set of discipline-specific tags, and export results to CSV or JSON formats. An integrated back-end database stores tagging data for comparison between taggers or visual display of results on the web browser. While other discipline-specific text tagging tools exist, the authors have not encountered a cloud-based customizable tool for PDF and text annotation as flexible as the AFLEX Tag Tool developed by the authors.
Comments
This proceeding is published as Ramezani, M., V. Kalivarapu, S. B. Gilbert, S. Huffman, E. Cotos, and A. O'Conner. "Rapid Tagging and Reporting for Functional Language Extraction in Scientific Articles." In Proceedings of the 6th International Workshop on Mining Scientific Publications, pp. 34-39. ACM, 2017. DOI: 10.1145/3127526.3127533. Posted with permission.