# Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking

arXiv: https://arxiv.org/abs/2107.11778 · HTML: https://mlsanity.com/paper/2107.11778/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 25 Jul 2021.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Pointer Networks](https://mlsanity.com/paper/1506.03134/) (2015)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues](https://mlsanity.com/paper/1605.06069/) (2016)
- [Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://mlsanity.com/paper/1606.03777/) (2016)
- [Efficient Dialogue State Tracking by Selectively Overwriting Memory](https://mlsanity.com/paper/1911.03906/) (2019)
- [SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking](https://mlsanity.com/paper/1907.07421/) (2019)
- [A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks](https://mlsanity.com/paper/1611.01587/) (2016)
- [Dialog State Tracking: A Neural Reading Comprehension Approach](https://mlsanity.com/paper/1908.01946/) (2019)
- [Global-Locally Self-Attentive Dialogue State Tracker](https://mlsanity.com/paper/1805.09655/) (2018)
- [Pointing the Unknown Words](https://mlsanity.com/paper/1603.08148/) (2016)
- [Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing](https://mlsanity.com/paper/1807.06517/) (2018)
- [An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking](https://mlsanity.com/paper/1805.01555/) (2018)
- [Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation](https://mlsanity.com/paper/1909.00754/) (2019)
- [HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking](https://mlsanity.com/paper/1907.00883/) (2019)
- [Scalable Neural Dialogue State Tracking](https://mlsanity.com/paper/1910.09942/) (2019)

## Abstract (arXiv)

Recently, researchers have explored using the encoder-decoder framework to tackle dialogue state tracking (DST), which is a key component of task-oriented dialogue systems. However, they regard a multi-turn dialogue as a flat sequence, failing to focus on useful information when the sequence is long. In this paper, we propose a Hierarchical Dynamic Copy Network (HDCN) to facilitate focusing on the most informative turn, making it easier to extract slot values from the dialogue context. Based on the encoder-decoder framework, we adopt a hierarchical copy approach that calculates two levels of attention at the word- and turn-level, which are then renormalized to obtain the final copy distribution. A focus loss term is employed to encourage the model to assign the highest turn-level attention weight to the most informative turn. Experimental results show that our model achieves 46.76% joint accuracy on the MultiWOZ 2.1 dataset.