For my AI-Driven Web Text Simplification research, I lead a coalition of corporate and academic partners. They include:
Make Web text so simple people understand it the first time they read it.
Text comprises the vast majority of Web content. Poor reading comprehension presents significant challenges to many populations, including people with cognitive disabilities, non‐native speakers, and people with low literacy.
Text simplification aims to reduce text complexity while retaining its meaning. Manual text simplification research has been ongoing for decades. Yet no significant effort has been made to automate text simplification except as a preprocessor for natural-language processing tasks such as machine translation and summarization.
In the short term, my partners and I are improving manual text simplification by creating effective, replicable methods for humans to produce it. We use national and international plain language standards. We conduct pilot studies to see if people comprehend our human-curated, simplified Web text better than typical Web text.
In the long term, my partners and I are developing artificial intelligence (AI) capabilities to produce simple Web text on a mass scale. We are training AI with enormous sets of aligned sentence pairs (typical/simple). We will soon start crowd-sourcing the generation of training data.
I will provide details in future blog posts.
Register Now for the 2018 Boston Accessibility Conference!
This is a conference about making technology accessible, especially the Web. It is an opportunity for programmers, designers, developers, usability professionals, accessibility experts, and end users to share information and learn from each other.
Keynote Speaker:
Organizers:
2018 sponsors include my own program, INDEX, which has free information about programs, providers, and services for people with disabilities in Massachusetts. See DisabilityInfo.org. We build accessible Web applications and online courses. See INDEX Technical Services. We also develop mass-scale, artificial-intelligence-driven Web text simplification for people with cognitive disabilities.
Register Now for the 2016 Boston Accessibility Conference!
This is a conference about making technology accessible, especially the web, but also mobile, games, and much more. It is an opportunity for designers, developers, usability professionals, accessibility experts, and end users to share information and learn from each other.
Keynote Speaker:
Organizers include:
2016 sponsors include my own program, INDEX, which has free information about programs, providers, and services for people with disabilities in Massachusetts. We also build accessible web applications and online courses.
Yesterday, Neil Milliken and Debra Ruh, members of the W3C‘s Cognitive and Learning Disabilities Accessibility Task Force, interviewed Andrew Imparato, Executive Director of the U.S. Association of University Centers on Disabilities as part of their AXSchat series.
Watch the great, informative interview of Andy. Their discussion is a wide-ranging one, including commentary about related U.S. policy, and the history of its development.
The programs they discussed are the very ones in which I have worked, since 1991, at the Eunice Kennedy Shriver Center.
Register Now for the 2015 Boston Accessibility Conference!
This is a conference about making technology accessible, especially the web, but also mobile, games, and much more. It is an opportunity for designers, developers, usability professionals, accessibility experts, and end users to share information and learn from each other.
Keynote Speaker:
Organizers include:
2015 sponsors include my own program, INDEX, which provides, to the public for free, information about programs, providers, and services for people with disabilities in Massachusetts. We also build accessible web applications and online courses.
Neil Milliken and I have written an autism gap analysis as part of the effort to create gap analyses by the W3C‘s Cognitive and Learning Disabilities Accessibility Task Force. Our intent is to identify the gap between where the state of accessibility for people with autism is now when using the web, and where we want it to be. The following is information about the autism gap analysis.
We included some personas with use cases that address key challenges. The personas and use cases are based upon aggregated results of interviews of people with autism-spectrum disorder (ASD), and upon anecdotal observations of their use of the web.
To our knowledge, there is no significant, empirical (user-based) testing on the use of the web by people with autism or other cognitive disabilities. In part because of that, we quoted results of directly-related research performed by WebAIM (N=8) in the section “Characteristics of content optimized for this group.”
We also quoted, from authoritative sources, much of the background information about autism. We did that, in large part, to help avoid adding to ASD-related controversies. The prime example is the reported increasing prevalence of ASD, and arguments that the increase is not actual, but due to the nature of the diagnoses.
Notes:
The members of the W3C‘s Cognitive and Learning Disabilities Accessibility Task Force have been working since January to develop a set of gap analyses. A gap analysis, as we have defined it, identifies the gap between where the state of accessibility for people with cognitive disabilities is now when using the web, and where we want it to be.
The gap analyses are based upon common cognitive disabilities. The following list of the gap analyses includes their primary authors (as of July, 2014).
The task force has completed the first drafts. We are now working on integrating the information in the gap analyses into a single document. A large part of this work is to define cognitive web accessibility from a functional standpoint. We plan to combine information, such as challenges and techniques, that is common across the gap analyses, and retain information that is unique to a particular disability.
Note: The referenced gap analyses should not be quoted. They are works in progress. They do not necessarily represent consensus. They may have incorrect information; or information not supported by other task-force members, the WAI, or the W3C. They also may have some very-useful information. (This disclaimer paraphrases the one at the tops of the gap analyses.)
Register Now for the 2014 Boston Accessibility Conference!
This is a conference about making technology accessible, especially the web, but also mobile, games, and much more. It is an opportunity for designers, developers, usability professionals, accessibility experts, and end users to share information and learn from each other.
Keynote Speaker:
Organizers include:
2014 sponsors include my own project, INDEX, which provides, to the public for free, information about programs, providers, and services for people with disabilities in Massachusetts.
Register Now for the 2013 Boston Accessibility Conference!
This is a conference about making technology accessible, especially the web, but also mobile, games, and much more. It is an opportunity for designers, developers, usability professionals, accessibility experts, and end users to share information and learn from each other.
Organizers include:
2013 sponsors include my own project, INDEX, which provides, to the public for free, information about programs, providers, and services for people with disabilities in Massachusetts.
