English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We aim to help users communicate their intent to machines using flexible,adaptive interfaces that translate arbitrary user input into desired actions.In this work, we focus on assistive typing applications in which a user cannotoperate a keyboard, but can instead supply other inputs, such as webcam imagesthat capture eye gaze or neural activity measured by a brain implant. Standardmethods train a model on a fixed dataset of user inputs, then deploy a staticinterface that does not learn from its mistakes; in part, because extracting anerror signal from user behavior can be challenging. We investigate a simpleidea that would enable such interfaces to improve over time, with minimaladditional effort from the user: online learning from user feedback on theaccuracy of the interface's actions. In the typing domain, we leveragebackspaces as feedback that the interface did not perform the desired action.We propose an algorithm called x-to-text (X2T) that trains a predictive modelof this feedback signal, and uses this model to fine-tune any existing, defaultinterface for translating user input into actions that select words orcharacters. We evaluate X2T through a small-scale online user study with 12participants who type sentences by gazing at their desired words, a large-scaleobservational study on handwriting samples from 60 users, and a pilot studywith one participant using an electrocorticography-based brain-computerinterface. The results show that X2T learns to outperform a non-adaptivedefault interface, stimulates user co-adaptation to the interface, personalizesthe interface to individual users, and can leverage offline data collected fromthe default interface to improve its initial performance and accelerate onlinelearning.

X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback