# MA-DST: Multi-Attention Based Scalable Dialog State Tracking

arXiv: https://arxiv.org/abs/2002.08898 · HTML: https://mlsanity.com/paper/2002.08898/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Feb 2020.

## Built on by (most cited first, 24 of 24)

- [CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems](https://mlsanity.com/paper/2103.15721/) (2021)
- [Zero-Shot Dialogue State Tracking via Cross-Task Transfer](https://mlsanity.com/paper/2109.04655/) (2021)
- [SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems](https://mlsanity.com/paper/2110.06800/) (2021)
- [Large Language Models as Zero-shot Dialogue State Tracker through Function Calling](https://mlsanity.com/paper/2402.10466/) (2024)
- [Zero-shot Generalization in Dialog State Tracking through Generative Question Answering](https://mlsanity.com/paper/2101.08333/) (2021)
- [NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation](https://mlsanity.com/paper/2105.14454/) (2021)
- [Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue](https://mlsanity.com/paper/2204.04327/) (2022)
- [Robust Dialogue State Tracking with Weak Supervision and Sparse Data](https://mlsanity.com/paper/2202.03354/) (2022)
- [Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2306.00434/) (2023)
- [FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis](https://mlsanity.com/paper/2210.15360/) (2022)
- [DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning](https://mlsanity.com/paper/2212.02851/) (2022)
- [Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation](https://mlsanity.com/paper/2306.04724/) (2023)
- [Reasoning-Enhanced Object-Centric Learning for Videos](https://mlsanity.com/paper/2403.15245/) (2024)
- [Instilling Type Knowledge in Language Models via Multi-Task QA](https://mlsanity.com/paper/2204.13796/) (2022)
- [InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2310.08885/) (2023)
- [Attention Guided Dialogue State Tracking with Sparse Supervision](https://mlsanity.com/paper/2101.11958/) (2021)
- [Diable: Efficient Dialogue State Tracking as Operations on Tables](https://mlsanity.com/paper/2305.17020/) (2023)
- [An Adversarial Learning based Multi-Step Spoken Language Understanding System through Human-Computer Interaction](https://mlsanity.com/paper/2106.14611/) (2021)
- [XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking](https://mlsanity.com/paper/2204.05895/) (2022)
- [SF-DST: Few-Shot Self-Feeding Reading Comprehension Dialogue State Tracking with Auxiliary Task](https://mlsanity.com/paper/2209.07742/) (2022)
- [Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking](https://mlsanity.com/paper/2302.13013/) (2023)
- [Ontology-Enhanced Slot Filling](https://mlsanity.com/paper/2108.11275/) (2021)
- [Improving Dialogue State Tracking by Joint Slot Modeling](https://mlsanity.com/paper/2109.14144/) (2021)
- [HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST](https://mlsanity.com/paper/2509.19742/) (2025)

## Abstract (arXiv)

Task oriented dialog agents provide a natural language interface for users to complete their goal. Dialog State Tracking (DST), which is often a core component of these systems, tracks the system's understanding of the user's goal throughout the conversation. To enable accurate multi-domain DST, the model needs to encode dependencies between past utterances and slot semantics and understand the dialog context, including long-range cross-domain references. We introduce a novel architecture for this task to encode the conversation history and slot semantics more robustly by using attention mechanisms at multiple granularities. In particular, we use cross-attention to model relationships between the context and slots at different semantic levels and self-attention to resolve cross-domain coreferences. In addition, our proposed architecture does not rely on knowing the domain ontologies beforehand and can also be used in a zero-shot setting for new domains or unseen slot values. Our model improves the joint goal accuracy by 5% (absolute) in the full-data setting and by up to 2% (absolute) in the zero-shot setting over the present state-of-the-art on the MultiWoZ 2.1 dataset.