Action State Update Approach to Dialogue Management
This work addresses utterance interpretation for dialogue systems, but it appears incremental as it builds on existing methods without a major paradigm shift.
The paper tackles the problem of interpreting user utterances in dialogue systems, particularly those with referring expressions, by proposing the action state update approach (ASU) that uses a statistically trained binary classifier and active learning for training, and demonstrates successful interpretation through user-simulated and interactive human evaluations.
Utterance interpretation is one of the main functions of a dialogue manager, which is the key component of a dialogue system. We propose the action state update approach (ASU) for utterance interpretation, featuring a statistically trained binary classifier used to detect dialogue state update actions in the text of a user utterance. Our goal is to interpret referring expressions in user input without a domain-specific natural language understanding component. For training the model, we use active learning to automatically select simulated training examples. With both user-simulated and interactive human evaluations, we show that the ASU approach successfully interprets user utterances in a dialogue system, including those with referring expressions.