Offline and Online Satisfaction Prediction in Open-Domain Conversational Systems
This addresses the need for more responsive conversational agents by providing a method to predict user satisfaction, enabling real-time adaptation, though it is incremental as it builds on existing satisfaction prediction approaches.
The paper tackled the problem of predicting user satisfaction in open-domain conversational systems, proposing ConvSAT, a model that aggregates multiple conversation representations, and showed it significantly improves satisfaction prediction in both offline and online settings compared to state-of-the-art methods on datasets like Dialogue Breakdown Detection Challenge and Alexa Prize.
Predicting user satisfaction in conversational systems has become critical, as spoken conversational assistants operate in increasingly complex domains. Online satisfaction prediction (i.e., predicting satisfaction of the user with the system after each turn) could be used as a new proxy for implicit user feedback, and offers promising opportunities to create more responsive and effective conversational agents, which adapt to the user's engagement with the agent. To accomplish this goal, we propose a conversational satisfaction prediction model specifically designed for open-domain spoken conversational agents, called ConvSAT. To operate robustly across domains, ConvSAT aggregates multiple representations of the conversation, namely the conversation history, utterance and response content, and system- and user-oriented behavioral signals. We first calibrate ConvSAT performance against state of the art methods on a standard dataset (Dialogue Breakdown Detection Challenge) in an online regime, and then evaluate ConvSAT on a large dataset of conversations with real users, collected as part of the Alexa Prize competition. Our experimental results show that ConvSAT significantly improves satisfaction prediction for both offline and online setting on both datasets, compared to the previously reported state-of-the-art approaches. The insights from our study can enable more intelligent conversational systems, which could adapt in real-time to the inferred user satisfaction and engagement.