# HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking

arXiv: https://arxiv.org/abs/1907.00883 · HTML: https://mlsanity.com/paper/1907.00883/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2019.

## Built on by (most cited first, 14 of 14)

- ["Do you follow me?": A Survey of Recent Approaches in Dialogue State Tracking](https://mlsanity.com/paper/2207.14627/) (2022)
- [Few Shot Dialogue State Tracking using Meta-learning](https://mlsanity.com/paper/2101.06779/) (2021)
- [Task-Oriented Dialogue System as Natural Language Generation](https://mlsanity.com/paper/2108.13679/) (2021)
- [Common Ground Tracking in Multimodal Dialogue](https://mlsanity.com/paper/2403.17284/) (2024)
- [Integrating Dialog History into End-to-End Spoken Language Understanding Systems](https://mlsanity.com/paper/2108.08405/) (2021)
- [Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking](https://mlsanity.com/paper/2205.10059/) (2022)
- [Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?](https://mlsanity.com/paper/2105.03571/) (2021)
- [Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State Tracking](https://mlsanity.com/paper/2203.03123/) (2022)
- [OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue](https://mlsanity.com/paper/2209.04595/) (2022)
- [SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching](https://mlsanity.com/paper/2110.11514/) (2021)
- [ShopTalk: A System for Conversational Faceted Search](https://mlsanity.com/paper/2109.00702/) (2021)
- [Efficient Dialogue State Tracking by Masked Hierarchical Transformer](https://mlsanity.com/paper/2106.14433/) (2021)
- [Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking](https://mlsanity.com/paper/2107.11778/) (2021)
- [Candidate Attended Dialogue State Tracking Using BERT](https://mlsanity.com/paper/2607.16021/) (2026)

## Abstract (arXiv)

Recent works on end-to-end trainable neural network based approaches have demonstrated state-of-the-art results on dialogue state tracking. The best performing approaches estimate a probability distribution over all possible slot values. However, these approaches do not scale for large value sets commonly present in real-life applications and are not ideal for tracking slot values that were not observed in the training set. To tackle these issues, candidate-generation-based approaches have been proposed. These approaches estimate a set of values that are possible at each turn based on the conversation history and/or language understanding outputs, and hence enable state tracking over unseen values and large value sets however, they fall short in terms of performance in comparison to the first group. In this work, we analyze the performance of these two alternative dialogue state tracking methods, and present a hybrid approach (HyST) which learns the appropriate method for each slot type. To demonstrate the effectiveness of HyST on a rich-set of slot types, we experiment with the recently released MultiWOZ-2.0 multi-domain, task-oriented dialogue-dataset. Our experiments show that HyST scales to multi-domain applications. Our best performing model results in a relative improvement of 24% and 10% over the previous SOTA and our best baseline respectively.