Description

To-do lists have been found to be the most popular personal information management tools, yet there is no automated system to interpret and act upon them when appropriate on behalf of the user.

In this project, we are investigating how to assist users with to-do lists. Our goal is to assist users by mapping to-dos into capabilities of agents or services that could carry out the task that the user intends. Automating to-do lists is challenging, not only because they are specified as free text but also because most items contain abbreviated tasks, many do not specify an action to be performed, and often refer to unrelated (personal) items.

We are developing Beamer, a system for interpreting to-do lists by mapping items to structured tasks that agents can perform on behalf of users. Beamer uses paraphrase patterns to match to-do entries into agent capabilities. Our evaluations have shown that this approach works remarkably well, and can handle the concise expressions and idiosyncratic grammar of to-dos.

More (Research)