SciA11y: Converting Scientific Papers to Accessible HTML

We present SciA11y, a system that renders inaccessible scientific paper PDFs into HTML. SciA11y uses machine learning models to extract and understand the content of scientific PDFs, and reorganizes the resulting paper components into a form that better supports skimming and scanning for blind and low vision (BLV) readers. SciA11y adds navigation features such as tagged headings, a table of contents, and bidirectional links between inline citations and references, which allow readers to resolve citations without losing their context. A set of 1.5 million open access papers are processed and available at https://scia11y.org/. This system is a first step in addressing scientific PDF accessibility, and may significantly improve the experience of paper reading for BLV users.

[1]  Marti A. Hearst,et al.  Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols , 2020, CHI.

[2]  Waleed Ammar,et al.  Extracting Scientific Figures with Distantly Supervised Neural Networks , 2018, JCDL.

[3]  Yu Fang,et al.  ICDAR 2019 Competition on Table Detection and Recognition (cTDaR) , 2019, 2019 International Conference on Document Analysis and Recognition (ICDAR).

[4]  María Andrade-Aréchiga,et al.  MathML to ASCII-Braille and Hierarchical Tree Converter , 2010, ICCHP.

[5]  Gerhard Weber,et al.  SVGPlott: an accessible tool to generate highly adaptable, accessible audio-tactile charts for and from blind and visually impaired people , 2019, PETRA.

[6]  Daniel S. Weld,et al.  Improving the Accessibility of Scientific Documents: Current State, User Needs, and a System Solution to Enhance Scientific PDF Accessibility for Blind and Low Vision Users , 2021, ArXiv.

[7]  Kyle Lo,et al.  S2ORC: The Semantic Scholar Open Research Corpus , 2020, ACL.

[8]  Peng Wu,et al.  Accessible bar charts for visually impaired users , 2008 .

[9]  Lucian Popa,et al.  Global Table Extractor (GTE): A Framework for Joint Table Identification and Cell Structure Recognition Using Visual Context , 2020, ArXiv.

[10]  Philippe A. Palanque,et al.  Making the field of computing more inclusive , 2017, Commun. ACM.

[11]  Volker Sorge,et al.  Towards making mathematics a first class citizen in general screen readers , 2014, W4A.

[12]  Doug Downey,et al.  Incorporating Visual Layout Structures for Scientific Text Classification , 2021, ArXiv.

[13]  Gerhard Weber,et al.  Towards Accessible Charts for Blind and Partially Sighted People , 2017, Mensch & Computer.

[14]  Peng Gao,et al.  PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML , 2021, ArXiv.

[15]  Laurent Romary,et al.  GROBID - Information Extraction from Scientific Publications , 2015, ERCIM News.

[16]  Doug Downey,et al.  Construction of the Literature Graph in Semantic Scholar , 2018, NAACL.

[17]  Dominik Spinczyk,et al.  Multimedia platform for mathematics’ interactive learning accessible to blind people , 2018, Multimedia Tools and Applications.

[18]  Enda Bates,et al.  Spoken Mathematics Using Prosody, Earcons and Spearcons , 2010, ICCHP.

[19]  David A. Shamma,et al.  An Uninteresting Tour Through Why Our Research Papers Aren't Accessible , 2016, CHI Extended Abstracts.