DARPA Communicator: Cross System Results for the 2001 Evaluation

Marilyn Walker, Alex Rudnicky, John Aberdeen, E Bratt, J Garofolo, Helen Wright Hastie, A Le, B Pellom, A Potamianos, Rebecca Passonneau, Rashmi Prasad, S Roukos, G Sanders, Stephanie Seneff, D Stallard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

This paper describes the evaluation methodology and results of the 2001 DARPA Communicator evaluation. The experiment spanned 6 months of 2001 and involved eight DARPA Communicator systems in the travel planning domain. It resulted in a corpus of 1242 dialogs which include many more dialogues for complex tasks than the 2000 evaluation. We describe the experimental design, the approach to data collection, and the results. We compare the results by the type of travel plan and by system. The results demonstrate some large differences across sites and show that the complex trips are clearly more difficult.
Original languageEnglish
Title of host publicationProc. 7th International Conference on Spoken Language Processing (ICSLP 2002)
PublisherISCA
Pages269-272
DOIs
Publication statusPublished - 2002
Event7th International Conference on Spoken Language Processing (Interspeech 2002) - Denver, CO, United States
Duration: 16 Sept 200220 Sept 2002

Conference

Conference7th International Conference on Spoken Language Processing (Interspeech 2002)
Country/TerritoryUnited States
CityDenver, CO
Period16/09/0220/09/02

Fingerprint

Dive into the research topics of 'DARPA Communicator: Cross System Results for the 2001 Evaluation'. Together they form a unique fingerprint.

Cite this