CALO
- 3 min read
- 3 chapters
Related on Lably
Through Virtual assistant
The CALO effort has had many major spin-offs, most notably the Siri intelligent software assistant that is now part of the Apple iOS since iOS 5, delivered in several phones and tablets; Social Kinetics, a social application that learned personalized intervention and treatment strategies for chronic disease patients, sold to RedBrick Health; the Trapit project, which is a web scraper and news aggregator that makes intelligent selections of web content based on user preferences; Tempo AI, a smart calendar; Desti, a personalized travel guide; and Kuato Studios, a game development startup.
CALO was funded by the Defense Advanced Research Projects Agency (DARPA) under its Personalized Assistant that Learns (PAL) program. DARPA's five-year contract brought together over 300 researchers from 25 of the top university and commercial research institutions, with the goal of building a new generation of cognitive assistants that can reason, learn from experience, be told what to do, explain what they are doing, reflect on their experience, and respond robustly to surprise. SRI International was the lead integrator responsible for coordinating the effort to produce an assistant that can live with and learn from its users, provide value to them, and then pass a yearly evaluation that measures how well the system has learned to do its job.
Functions
CALO assists its user with six high-level functions:
- Organizing and Prioritizing Information: As the user works with email, appointments, web pages, files, and so forth, CALO uses machine learning algorithms to build a queryable model of who works on which projects, what role they play, how important they are, how documents and deliverables are related to this, etc.
- Preparing Information Artifacts: CALO can help its user put together new documents such as PowerPoint presentations, leveraging learning about structure and content from previous documents accessed in the past.
- Mediating Human Communications: CALO provides assistance as its user interacts with other people, both in electronic forums (e.g. email) and in physical meetings. If given access to participate in a meeting, CALO automatically generates a meeting transcript, tracks action item assignments, detects roles of participants, and so forth. CALO can also put together a "PrepPak" for a meeting containing information to read ahead of time or have at your fingertips as the meeting progresses.
- Task Management: CALO can automate routine tasks for you (e.g. travel authorizations), and can be taught new procedures and tasks by observing and interacting with the user.
- Scheduling and Reasoning in Time: CALO can learn your preferences for when you need things done by, and help you manage your busy schedule (PTIME published in ACM TIST).
- Resource allocation: As part of Task management, CALO can learn to acquire new resources (electronic services and real-world people) to help get a job done.
Sign in to keep reading
2 more chapters are free with a Lably account.
Evaluation
Every year, the CALO system, after living with its user for a period of time, is given an achievement-style test of 153 "administration assistant" questions, primarily focused on what it has learned about the user's life. Evaluators measure how well CALO's performance on these questions improves year-over-year, and how much of CALO's performance is due to "learning in the wild" (new knowledge, tasks, and inferences it has been able to acquire on its own, as opposed to function or knowledge hard-wired into the system by a developer).
Framework
SRI International made a collection of successful machine learning and reasoning technologies developed in the PAL program, primarily from the CALO project, available online. The available technologies include both general-purpose learning methods along with more focused learning applications. The PAL software and related publications are available at the PAL Framework website.
The PAL capabilities have been modularized, packaged, and adapted to industry standards to facilitate their incorporation into target applications. Various infrastructure components and APIs are available to simplify interaction with the technologies. PAL capabilities were integrated into the US Army's CPOF command and control system and fielded to Iraq in 2010.
The available technologies were developed by research teams at SRI International, Carnegie Mellon University, the University of Massachusetts Amherst, the University of Rochester, the Institute for Human and Machine Cognition, Oregon State University, the University of Southern California, Xerox PARC and Stanford University.