# Parallel Interactive Networks for Multi-Domain Dialogue State Generation

arXiv: https://arxiv.org/abs/2009.07616 · HTML: https://mlsanity.com/paper/2009.07616/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [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)
- [LUNA: Learning Slot-Turn Alignment for Dialogue State Tracking](https://mlsanity.com/paper/2205.02550/) (2022)
- [Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking](https://mlsanity.com/paper/2107.12578/) (2021)
- [MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking](https://mlsanity.com/paper/2211.05503/) (2022)
- [Personalized Federated Learning via Gradient Modulation for Heterogeneous Text Summarization](https://mlsanity.com/paper/2304.11524/) (2023)

## Abstract (arXiv)

The dependencies between system and user utterances in the same turn and across different turns are not fully considered in existing multidomain dialogue state tracking (MDST) models. In this study, we argue that the incorporation of these dependencies is crucial for the design of MDST and propose Parallel Interactive Networks (PIN) to model these dependencies. Specifically, we integrate an interactive encoder to jointly model the in-turn dependencies and cross-turn dependencies. The slot-level context is introduced to extract more expressive features for different slots. And a distributed copy mechanism is utilized to selectively copy words from historical system utterances or historical user utterances. Empirical studies demonstrated the superiority of the proposed PIN model.