# A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking

arXiv: https://arxiv.org/abs/2006.01554 · HTML: https://mlsanity.com/paper/2006.01554/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jun 2020.

## Built on by (most cited first, 20 of 20)

- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation](https://mlsanity.com/paper/2104.00773/) (2021)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances](https://mlsanity.com/paper/2106.02227/) (2021)
- [Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking](https://mlsanity.com/paper/2106.00291/) (2021)
- [Slot Self-Attentive Dialogue State Tracking](https://mlsanity.com/paper/2101.09374/) (2021)
- [Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking](https://mlsanity.com/paper/2104.04466/) (2021)
- [Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.08570/) (2021)
- [ASSIST: Towards Label Noise-Robust Dialogue State Tracking](https://mlsanity.com/paper/2202.13024/) (2022)
- [Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations](https://mlsanity.com/paper/2107.05168/) (2021)
- [DEBACER: a method for slicing moderated debates](https://mlsanity.com/paper/2112.05438/) (2021)
- [LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking](https://mlsanity.com/paper/2205.02550/) (2022)
- [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)
- [Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking](https://mlsanity.com/paper/2107.12578/) (2021)
- [A Context-Aware Hierarchical BERT Fusion Network for Multi-turn Dialog Act Detection](https://mlsanity.com/paper/2109.01267/) (2021)
- [An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker](https://mlsanity.com/paper/2101.11360/) (2021)
- [Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2208.02462/) (2022)
- [Efficient Dialogue State Tracking by Masked Hierarchical Transformer](https://mlsanity.com/paper/2106.14433/) (2021)

## Abstract (arXiv)

Recent studies in dialogue state tracking (DST) leverage historical information to determine states which are generally represented as slot-value pairs. However, most of them have limitations to efficiently exploit relevant context due to the lack of a powerful mechanism for modeling interactions between the slot and the dialogue history. Besides, existing methods usually ignore the slot imbalance problem and treat all slots indiscriminately, which limits the learning of hard slots and eventually hurts overall performance. In this paper, we propose to enhance the DST through employing a contextual hierarchical attention network to not only discern relevant information at both word level and turn level but also learn contextual representations. We further propose an adaptive objective to alleviate the slot imbalance problem by dynamically adjust weights of different slots during training. Experimental results show that our approach reaches 52.68% and 58.55% joint accuracy on MultiWOZ 2.0 and MultiWOZ 2.1 datasets respectively and achieves new state-of-the-art performance with considerable improvements (+1.24% and +5.98%).