# Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition

arXiv: https://arxiv.org/abs/2004.10663 · HTML: https://mlsanity.com/paper/2004.10663/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [EtriCA: Event-Triggered Context-Aware Story Generation Augmented by Cross Attention](https://mlsanity.com/paper/2210.12463/) (2022)
- [Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges](https://mlsanity.com/paper/2505.13328/) (2025)
- [SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation](https://mlsanity.com/paper/2405.15924/) (2024)
- [Improving Medical Dialogue Generation with Abstract Meaning Representations](https://mlsanity.com/paper/2309.10608/) (2023)
- [A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions](https://mlsanity.com/paper/2504.16939/) (2025)
- [Terminology-aware Medical Dialogue Generation](https://mlsanity.com/paper/2210.15551/) (2022)
- [CADGE: Context-Aware Dialogue Generation Enhanced with Graph-Structured Knowledge Aggregation](https://mlsanity.com/paper/2305.06294/) (2023)
- [Evaluating Open-Domain Dialogues in Latent Space with Next Sentence Prediction and Mutual Information](https://mlsanity.com/paper/2305.16967/) (2023)
- [A Cross-Attention Augmented Model for Event-Triggered Context-Aware Story Generation](https://mlsanity.com/paper/2311.11271/) (2023)
- [Affective Decoding for Empathetic Response Generation](https://mlsanity.com/paper/2108.08102/) (2021)

## Abstract (arXiv)

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.