Abstract
Proposed herein is a novel, passive approach for monitoring user satisfaction for interactions with a Natural Language Interface (NLI) system. Specifically, a novel architecture or system is proposed through which satisfaction metrics can be leveraged to actively monitor NLI performance. In some instances, automatic retraining processes may be activated, if necessary. Thus, the system may ensure a continuous enhancement of an NLI, which may lead to an elevated user experience without the need of external user or administrator intervention.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Karygianni, Sofia; Weibel, Yannick; and Stirling, Timothy, "PASSIVE USER SATISFACTION MONITORING FOR PERFORMANCE EVALUATION OF NATURAL LANGUAGE INTERFACE SYSTEMS", Technical Disclosure Commons, (May 06, 2024)
https://www.tdcommons.org/dpubs_series/6968