Diable: Efficient Dialogue State Tracking as Operations on Tables
This addresses efficiency issues in dialogue state tracking for conversational AI systems, though it is an incremental improvement over existing methods.
The authors tackled the inefficiency of sequence-to-sequence dialogue state tracking systems by proposing Diable, which formalizes DST as table operations, resulting in a 2.4x improvement in time efficiency while maintaining competitive accuracy on MultiWoz datasets.
Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, and generate the entire state from scratch at each dialogue turn. This approach is inefficient, especially when the number of slots is large and the conversation is long. We propose Diable, a new task formalisation that simplifies the design and implementation of efficient DST systems and allows one to easily plug and play large language models. We represent the dialogue state as a table and formalise DST as a table manipulation task. At each turn, the system updates the previous state by generating table operations based on the dialogue context. Extensive experimentation on the MultiWoz datasets demonstrates that Diable (i) outperforms strong efficient DST baselines, (ii) is 2.4x more time efficient than current state-of-the-art methods while retaining competitive Joint Goal Accuracy, and (iii) is robust to noisy data annotations due to the table operations approach.