Send in your ideas. Deadline February 1, 2025
Grant
Theme fund: NGI0 Discovery
Period: 2020-12 — 2022-10
More projects like this
Services + Applications

Redash

Predictive text entry without a keyboard

This project is archived. Due to circumstances, the project as planned did not take place. This page is left as a placeholder, for transparency reasons and to perhaps inspire others to take up this work.

Dasher is an alternative text entry system that searches for suggestions without the discrete input through a keyboard. The software is invaluable to people with disabilities who use it to type or speak and who can’t control a regular physical or on-screen keyboard. Dasher is instead driven by continuous gesture using a dynamic predictive display, a concept originally developed by the University of Cambridge Inference group.

The dasher project aims to help all individuals with disabilities who use similar assistive technology by developing a modular word and letter prediction engine that is allows for a range of language models to be used - and new ones be trialed out, including potentially integration with context sensitive search prediction provided by search engine providers. The new dasher will provide a fresh codebase matching the features that current users require - whilst improving on the user experience for new users. Thanks to a permissive open source software license anyone will be able to develop additional innovations on top of dasher, including commercial entities that produce bespoke systems. This will help increase the ability for employers to hire people that depend on this type of input mechanisms.

    Why does this actually matter to end users?

    Do you think internet access is a universal human right? To benefit from online services and information, first you would need to be able to access the internet in a way that works for you. Unfortunately this is not always the case: people with disabilities face all sorts of challenges when they use websites, apps and technology that do not take their needs into appreciation. Experts estimate that a quarter of the online audience is (partially) disabled. On internet scale this means millions of people are potentially banned from using online devices and services, which is especially problematic if they have limited mobility and depend on help from others.

    Luckily support organizations and businesses have developed a range of support tools for people with disabilities to go online, like for example screen readers. Dasher is a tool stemming from academic research that allows you to enter text and search for suggestions without using a keyboard, instead entering text on a screen with a pointing device. This project will update the technology behind Dasher and improve how well its predictions work, potentially by integrating the suggestions provided by search engines. This can make Dasher quicker to use and more intuitive, which is especially helpful to people who rely on it for their communication using text-to-speech.

    Logo NLnet: abstract logo of four people seen from above Logo NGI Zero: letterlogo shaped like a tag

    This project was funded through the NGI0 Discovery Fund, a fund established by NLnet with financial support from the European Commission's Next Generation Internet programme, under the aegis of DG Communications Networks, Content and Technology under grant agreement No 825322.