TUGboat 44:3 (2023)
The Communications of the TeX Users Group

Title: Using artificial-intelligence tools to make LaTeX content accessible to blind readers

Summary: using GPT-4 to narrate typical LaTeX scientific documents.

Full text of article: publicly available now.

Author: Gerd Kortemeyer

Publication: TUGboat volume 44, number 3 (2023), pages 390–399

DOI (this page): 10.47397/tb/44-3/tb138kortemeyer-accessibility
(previous doi - next doi)

Category: Accessibility

Difficulty: Intermediate Plus

Abstract: Screen-reader software enables blind users to access large segments of electronic content, particularly if accessibility standards are followed. Unfortunately, this is not true for much of the content written in physics, mathematics, and other STEM disciplines, due to the strong reliance on mathematical symbols and expressions, which screen-reader software generally fails to process correctly.

A large portion of such content is based on source documents written in LaTeX, which are rendered to PDF or HTML for online distribution. Unfortunately, the resulting PDF documents are essentially inaccessible, and the HTML documents vary greatly in accessibility, since their accessibility-standards compliant rendering is cumbersome at best.

This paper explores the possibility of generating standards-compliant, accessible HTML from LaTeX sources using Large Language Models. It is found that the resulting documents are highly accessible, with possible complications occurring when the artificial intelligence tool starts to interpret the content.

References:

1. D. Ahmetovic, T. Armano, et al. Axessibility: A LaTeX package for mathematical formulae accessibility in PDF documents. In Proceedings of the 20th international ACM SIGACCESS conference on computers and accessibility, pp. 352–354, 2018. See also tug.org/TUGboat/tb39-3/tb123ahmetovic-axess.pdf
2. Y. Borodin, J.P. Bigham, et al. More than meets the eye: a survey of screen-reader browsing strategies. In Proceedings of the 2010 International Cross Disciplinary Conference on Web Accessibility (W4A), pp. 1–10, 2010.
3. D. Cervone. MathJax: a platform for mathematics on the web. Notices of the AMS, 59(2):312–316, 2012. doi.org/10.1090/noti794
4. D. Cervone, P. Krautzberger, V. Sorge. New accessibility features in MathJax. The Journal on Technology and Persons with Disabilities, 4:167–175, 2016.
5. Creative Commons. Share your work. creativecommons.org/share-your-work/
6. A. Darvishy. PDF accessibility: tools and challenges. In Computers Helping People with Special Needs: 16th International Conference, ICCHP 2018, Linz, Austria, July 11–13, 2018, Proceedings, Part I, pp. 113–116. Springer, 2018.
7. R. Fateman. How can we speak math. Journal of Symbolic Computation, 25(2), 1998.
8. J. Fenn. Managing citations and your bibliography with BibTeX. The PracTeX Journal, 4:2006–4, 2006. tug.org/pracjourn/2006-4/fenn
9. Free Software Foundation. What is free software? www.gnu.org/philosophy/free-sw.en.html
10. J. Gilligan. Competencies for educators in delivering digital accessibility in higher education. In Universal Access in Human-Computer Interaction. Applications and Practice: 14th International Conference, UAHCI 2020, Held as Part of the 22nd HCI International Conference, HCII 2020, Copenhagen, Denmark, July 19–24, 2020, Proceedings, Part II 22, pp. 184–199. Springer, 2020.
11. T. Groza, S. Handschuh, et al. SALT-semantically annotated LaTeX for scientific publications. In The Semantic Web: Research and Applications: 4th European Semantic Web Conference, ESWC 2007, Innsbruck, Austria, June 3–7, 2007. Proceedings 4, pp. 518–532. Springer, 2007.
12. S. Iwarsson, A. Ståhl. Accessibility, usability and universal design — positioning and definition of concepts describing person-environment relationships. Disability and rehabilitation, 25(2):57–66, 2003.
13. A. Jembu Rajkumar, J. Lazar, et al. PDF accessibility of research papers: What tools are needed for assessment and remediation? In Proceedings of the 53rd Hawaii International Conference on System Sciences (HICSS), 2020.
14. M. Kohlhase. Using LaTeX as a semantic markup format. Mathematics in Computer Science, 2(2):279–304, 2008.
15. G. Kortemeyer. Could an artificial-intelligence agent pass an introductory physics course? Phys. Rev. Phys. Educ. Res., 19:010132, May 2023. doi.org/10.1103/PhysRevPhysEducRes.19.010132
16. A. Manzoor, S. Arooj, et al. ALAP: Accessible LaTeX-based mathematical document authoring and presentation. In Proceedings of the 2019 CHI conference on human factors in computing systems, pp. 1–12, 2019.
17. J.T. Nganji. The Portable Document Format (PDF) accessibility practice of four journal publishers. Library & Information Science Research, 37(3):254–262, 2015.
18. A. Ogawa. RevTeX version 4.0, an authoring package by the American Physical Society. TUGboat 22(3):131–133, 2001. tug.org/TUGboat/tb22-3/tb71ogawa.pdf
19. OpenAI. GPT Release Notes. help.openai.com/en/articles/6825453-chatgpt-release-notes
20. H. Persson, H. Åhman, et al. Universal design, inclusive design, accessible design, design for all: different concepts—one goal? On the concept of accessibility—historical, methodological and philosophical aspects. Universal Access in the Information Society, 14:505–526, 2015.
21. A. Petz, K. Miesenberger. Supporting blind students in STEM education in Austria. In AAATE Conf., pp. 27–31, 2015.
22. Salt Lake Community College. Screen reader demo. www.youtube.com/watch?v=q_ATY9gimOM
23. V. Sorge, C. Chen, et al. Towards making mathematics a first class citizen in general screen readers. In Proceedings of the 11th web for all conference, pp. 1–10, 2014.
24. University of California San Francisco. Screen reader demo for digital accessibility. www.youtube.com/watch?v=dEbl5jvLKGQ
25. Z. Walczak. Graphics in LaTeX using TikZ. TUGboat 20:176–179, 2008. tug.org/TUGboat/tb29-1/tb91walczak.pdf
26. WWW Consortium (W3C). Web content accessibility guidelines (WCAG) 2.0. www.w3.org/TR/WCAG20/