# CREDIT: Coarse-to-Fine Sequence Generation for Dialogue State Tracking

arXiv: https://arxiv.org/abs/2009.10435 · HTML: https://mlsanity.com/paper/2009.10435/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Sep 2020.

## Built on by (most cited first, 5 of 5)

- [Summ^N: A Multi-Stage Summarization Framework for Long Input Dialogues and Documents](https://mlsanity.com/paper/2110.10150/) (2021)
- [Slot Self-Attentive Dialogue State Tracking](https://mlsanity.com/paper/2101.09374/) (2021)
- [Effective Sequence-to-Sequence Dialogue State Tracking](https://mlsanity.com/paper/2108.13990/) (2021)
- [Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL](https://mlsanity.com/paper/2106.02282/) (2021)
- [OPAL: Ontology-Aware Pretrained Language Model for End-to-End Task-Oriented Dialogue](https://mlsanity.com/paper/2209.04595/) (2022)

## Abstract (arXiv)

In dialogue systems, a dialogue state tracker aims to accurately find a compact representation of the current dialogue status, based on the entire dialogue history. While previous approaches often define dialogue states as a combination of separate triples (em domain-slot-value), in this paper, we employ a structured state representation and cast dialogue state tracking as a sequence generation problem. Based on this new formulation, we propose a bf Coabf Rsbf E-to-fine bf DIalogue state bf Tracking (bf CREDIT) approach. Taking advantage of the structured state representation, which is a marked language sequence, we can further fine-tune the pre-trained model (by supervised learning) by optimizing natural language metrics with the policy gradient method. Like all generative state tracking methods, CREDIT does not rely on pre-defined dialogue ontology enumerating all possible slot values. Experiments demonstrate our tracker achieves encouraging joint goal accuracy for the five domains in MultiWOZ 2.0 and MultiWOZ 2.1 datasets.