ACM Home Page
Please provide us with feedback. Feedback
A collaborative assistant for email
Full text PdfPdf (200 KB)
Source Conference on Human Factors in Computing Systems archive
CHI '99 extended abstracts on Human factors in computing systems table of contents
Pittsburgh, Pennsylvania
SESSION: Late-breaking results: novel collaborative paradigms table of contents
Pages: 196 - 197  
Year of Publication: 1999
ISBN:1-58113-158-5
Authors
Dan Gruen  Lotus Development Corporation, Cambridge, MA
Candy Sidner  Lotus Development Corporation, Cambridge, MA
Carolyn Boettner  Lotus Development Corporation, Cambridge, MA
Charles Rich  MERL -- Mitsubishi Electric Research Lab, Cambridge, MA
Sponsor
SIGCHI: ACM Special Interest Group on Computer-Human Interaction
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 10,   Downloads (12 Months): 23,   Citation Count: 7
Additional Information:

abstract   references   cited by   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/632716.632839
What is a DOI?

ABSTRACT

Software agents which communicate and collaborate with users to perform complex tasks constitute a new paradigm for human-computer interaction complementing existing graphical interfaces. We have recently completed a prototype agent of this kind for helping people with their email, based on our studies of people working with human assistants and Wizard-of-Oz studies. The prototype was constructed using application-independent software for modeling collaborative discourse (Collagen, see [4]) jointly developed by Lotus and Mitsubishi Electric and speech understanding technology from IBM Research. Users perform typical email tasks via a flexible combination of spoken language conversation with the agent and graphical interface actions (which are observed by the agent). The agent maintains a model of the user's goals and activities, and can act on its own initiative to assist the user. Having a high-level model of actions and goals allows speech to be used in a more natural, conversational, and effective manner than otherwise possible.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
 
2
Chung. G. And Seneff, S. "Improvements in Speech Understanding Accuracy through the Integration of Hierarchical Linguistic, Prosodic, and Phonological Constraints in the Jupiter Domain" ICSLP 98, Sydney, Australia, November 1998.
 
3
Lesh, N. Rich, C. & Sidner, C. Using Plan Recognition in Human-Computer Collaboration, Lotus TR 98-14, 1998
 
4
 
5

CITED BY  8

Collaborative Colleagues:
Dan Gruen: colleagues
Candy Sidner: colleagues
Carolyn Boettner: colleagues
Charles Rich: colleagues