Teaching a computer to type like a human

A new typing model simulates the typing process instead of just predicting words
Kuvakaappaus kahden puhelimen näytöstä, joihin on kirjoitettu tekstiä.
A screenshot of the typing model developed by researchers. Photo: Aalto University

An entirely new predictive typing model can simulate different kinds of users, helping figure out ways to optimize how we use our phones. Developed by researchers at Aalto University, the new model captures the difference between typing with one or two hands or between younger and older users.

‘Typing on a phone requires manual dexterity and visual perception: we press buttons, proofread text, and correct mistakes. We also use our working memory. Automatic text correction functions can help some people, while for others they can make typing harder,’ says Professor Antti Oulasvirta of Aalto University.

The researchers created a machine-learning model that uses its virtual ‘eyes and fingers’ and working memory to type out a sentence, just like humans do. That means it also makes similar mistakes and has to correct them.

‘We created a simulated user with a human-like visual and motor system. Then we trained it millions of times in a keyboard simulator. Eventually, it learned typing skills that can also be used to type in various situations outside the simulator,’ explains Oulasvirta.

The predictive typing model was developed in collaboration with Google. New designs for phone keyboards are normally tested with real users, which is costly and time-consuming. The project’s goal is to complement those tests so keyboards can be evaluated and optimized more quickly and easily.

For Oulasvirta, this is part of a larger effort to improve user interfaces overall and understand how humans behave in task-oriented situations. He leads a research group at Aalto that uses computational models of human behaviour to probe these questions.

‘We can train computer models so that we don’t need observation of lots of people to make predictions. User interfaces are everywhere today – fundamentally, this work aims to create a more functional society and smoother everyday life,’ he says.

The researchers will present their findings at the CHI Conference in May, the most prestigious scientific publication forum in the field of human-computer interaction. The peer-reviewed study is already available online.

Professor Antti Oulasvirta. Photo: Aalto University / Jaakko Kahilaniemi

Researchers investigate how AI could better understand humans

Antti Oulasvirta has received a EUR 2.5 million Advanced Grant by the European Research Council (ERC) for the study of user models.

Vertailu ihmisen ja tekoälymallin näppäilystä

AI learns to type on a phone like humans

Computational model precisely replicates eye and finger movements of touchscreen users -- could lead to better auto-correct and keyboard usability for unique needs


Aalto computer scientists in CHI 2024

Ten papers from Aalto CS were accepted to the CHI 2024 conference

  • Published:
  • Updated:

Read more news

Publication icon
Research & Art Published:

Publication Forum seeks new panellists for term 2025-2028

If you are interested in becoming a panel member of the Publication Forum (Julkaisufoorumi, Jufo), apply by 15.6.2024.
Matti Vartiainen
Research & Art Published:

New book on flexible hybrid work

Matti Vartiainen explores the shift in working culture and what it means for staff wellbeing and performance, as well as how remote work policies can be implemented effectively.
Textile Chemistry research group
Research & Art Published:

Making textiles greener, safer, and cooler

Professor Ali Tehrani and his research group focus on something very familiar to us all – textiles.
Campus Published:

PechaKucha event tested the presentation skills of doctoral students at the School of Electrical Engineering

The first PechaKucha at the School of Electrical Engineering challenged the school's doctoral students to present the topics of their dissertation in six minutes. The event was held on Wednesday 22 May at Otaniemi A Grid.