1 / 31

PLOW: A Collaborative Task Learning Agent

PLOW: A Collaborative Task Learning Agent. Author: James Allen, Nathanael Chambers, etc. By: Rex, Linger, Xiaoyi Nov. 23, 2009. Outline. Introduction The PLOW System Demonstration Learning Tasks Evaluation Strength & Weakness Related Works Q&A and Discussion. Introduction.

tova
Télécharger la présentation

PLOW: A Collaborative Task Learning Agent

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. PLOW: A Collaborative Task Learning Agent Author: James Allen, Nathanael Chambers, etc. By: Rex, Linger, Xiaoyi Nov. 23, 2009

  2. Outline • Introduction • The PLOW System • Demonstration • Learning Tasks • Evaluation • Strength & Weakness • Related Works • Q&A and Discussion

  3. Introduction • Aim to further human-machine interaction • Quickly learn new tasks from human subjects using modest amounts of interaction • Acquire task models from intuitive language-rich demonstration

  4. Background • Previous Work: Learn new tasks by observation, learn throw observing experts’ demonstration. • Paper’s Contribution: Acquire tasks much more quickly, typically from a single example, maybe with some clarification dialogue.

  5. The Interface

  6. Agent Architecture

  7. Language Processing • Focus on how it is used for task learning, rather than how it is accomplished • TRIPS system • Based on a domain-independent representation

  8. Instrumentation • The key issue is to get the right level of analysis for the instrumentation DOMs

  9. A demo

  10. Task Learning • Challenges • Identifying the correct parameterization • Hierarchical structure • Identifying the boundaries of iterative loops • Loop termination conditions • Task goals

  11. Primitive Action Learning • NL Interpretation + GUI Interpretation • Heuristic search through DOM • Semantic metric • Structural distance metric

  12. Primitive Action Learning Natural Language Interpretation Heuristic search GUI Interpretation Structural Distance Metric Semantic metric

  13. Parameterization Learning • Identify appropriate parameterization • Object roles • Input/output parameter • Constant • Relational dependency • Information from language

  14. Parameterization Learning • Output: Hotels • Input: Address • Constant: Hotels • Relational Dependency: Zip is Role of Address

  15. Hierarchical Structure Learning • Beginning of new procedures • A Goal • End of procedure

  16. Iteration Learning • Iterative procedure learning • Language support • PLOW’s attempt for Iteration • User corrections/more example • Rule/Pattern learned

  17. Iteration Learning

  18. Evaluation • 16 test subjects with general training • 3 other systems: • One learned entirely from passive observation • One used a sophisticated GUI primarily designed for editing procedures but extended to allow the definition of new procedures • One used an NL-like query and specification language that requires detailed knowledge of HTML producing the web page

  19. Evaluation – First part • Subjects taught different systems about some subset of predefined test questions • Evaluators created new test examples by specifying values for input parameters, then scored the execution results • PLOW scored 2.82 out of 4 (not mention other systems’ scores)

  20. Evaluation – Second part • 10 new test questions designed by an outside group, unknown to the developers prior to the test • Subjects had one work day to teach whichever of these tasks they wished, using whichever of the task learning system • PLOW was used to teach 30 out of 55 task models

  21. Evaluation – Second part • 10 new test questions designed by an outside group, unknown to the developers prior to the test • Subjects had one work day to teach whichever of these tasks they wished, using whichever of the task learning system • PLOW was used to teach 30 out of 55 task models • Also, PLOW received the highest average score in the test (2.2/4)

  22. Strength • Integrating natural language recognition and understanding (TRIPS, 2001) • “Play by play” mode, great user experience • Easier to identify parameters, boundaries of loops, termination conditions, build hierarchical structure, realize goals • Generalization from one short task • Learn not only the task, but also the rule

  23. Strength • Error correction from users • “This is wrong. Here is another title” • PLOW will confirm correctness from users when generating data from lists • Less domain knowledge required, less training • Close to “one-click automation”

  24. Weakness • Some remarks of Evaluation: • PLOW was ensured of being able to learn 17 pre-determined test questions, other systems? • 10 new tasks have different levels of difficulties: ex: For what reason did <person> travel for <project> between <start date> and <end date>? • No detailed analysis of evaluation result, so does PLOW really learn robust task models from a single example? Or just better on certain types of tasks?

  25. Weakness • Learning and reasoning relied on NL understanding: • encounters new concepts? • require certain patterns of speaking? Enough NL understanding capabilities? • Still need one full work day to teach 3 simple tasks/person • Users have to construct good task models, no error detection mechanism for users in PLOW

  26. Related works • Sheepdog, 2004 • an implemented system for capturing, learning, and playing back technical support procedures on the Windows desktop • Complex technical supporting procedures – relatively simple procedures in PLOW • Record traces to form alignment problem, use I/O HMMs to build procedure models, need many training examples

  27. Related works • Tailor, 2005 • a system that allows users to modify task information through instruction • Recognize user’s instruction: combine rules with parser, JavaNLP • Map sentences to hypothesized changes • Reason about the effects of changes, detect the unanticipated behavior • Also relatively simple tasks

  28. Related works • CHINLE, 2008 • a system which automatically constructs PBD systems for applications based on their interface specification • Learning from incomplete data and partial learning from inconsistent data – PLOW can learn subset of certain tasks, but users cannot make mistakes

  29. Questions?

  30. More time for the latest PLOW demo?

  31. Thank you!

More Related