A Supervised Approach To The Interpretation Of Imperative To-Do Lists
This work addresses the need for intelligent agents to support personal information management in electronic to-do lists, but it is incremental as it builds on existing work in personal assistants.
The paper tackled the problem of interpreting imperative to-do lists by classifying user intention and extracting information, showing that their methods perform well across two corpora, including one they released.
To-do lists are a popular medium for personal information management. As to-do tasks are increasingly tracked in electronic form with mobile and desktop organizers, so does the potential for software support for the corresponding tasks by means of intelligent agents. While there has been work in the area of personal assistants for to-do tasks, no work has focused on classifying user intention and information extraction as we do. We show that our methods perform well across two corpora that span sub-domains, one of which we released.