Modeling User Satisfaction Dynamics in Dialogue via Hawkes Process
This work addresses the challenge of automatic performance evaluation for dialogue systems, which is crucial for developers and researchers, though it is incremental as it builds on existing user satisfaction estimation methods.
The paper tackles the problem of evaluating dialogue systems by modeling user satisfaction dynamics across turns, proposing ASAP, which uses a Hawkes process to treat satisfaction as an event sequence and achieves substantial improvements over state-of-the-art baselines on four benchmark datasets.
Dialogue systems have received increasing attention while automatically evaluating their performance remains challenging. User satisfaction estimation (USE) has been proposed as an alternative. It assumes that the performance of a dialogue system can be measured by user satisfaction and uses an estimator to simulate users. The effectiveness of USE depends heavily on the estimator. Existing estimators independently predict user satisfaction at each turn and ignore satisfaction dynamics across turns within a dialogue. In order to fully simulate users, it is crucial to take satisfaction dynamics into account. To fill this gap, we propose a new estimator ASAP (sAtisfaction eStimation via HAwkes Process) that treats user satisfaction across turns as an event sequence and employs a Hawkes process to effectively model the dynamics in this sequence. Experimental results on four benchmark dialogue datasets demonstrate that ASAP can substantially outperform state-of-the-art baseline estimators.