Paper: Designing A Task-Based Evaluation Methodology For A Spoken Machine Translation System

ACL ID P99-1073
Title Designing A Task-Based Evaluation Methodology For A Spoken Machine Translation System
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1999
Authors

In this paper, I discuss issues pertinent to the design of a task-based evaluation methodology for a spoken machine translation (MT) sys- tem processing human to human communica- tion rather than human to machine communi- cation. I claim that system mediated human to human communication requires new evaluation criteria and metrics based on goal complexity and the speaker's prioritization of goals.