Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition
This work addresses the challenge of efficiently tracking dialogue states in complex, multi-turn conversations, which is incremental as it builds on existing methods by integrating them into a modular framework.
The paper tackles the problem of dialogue state tracking by proposing the Explicit Modular Decomposition (EMD) architecture, which combines classification-based and extraction-based methods to jointly extract dialogue states, achieving superior complexity and scalability compared to state-of-the-art methods on the MultiWoz 2.0 dataset, especially in multi-domain dialogues with many turns.
We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for classification and sequence labelling) to jointly extract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances.