Papers › Amendable Generation for Dialogue State Tracking

Amendable Generation for Dialogue State Tracking

29 Oct 2021EMNLP (NLP4ConvAI) 2021 11arXiv:2110.15659archive 2025-07-28

Xin Tian, Liankai Huang, Yingzhan Lin, Siqi Bao, Huang He, Yunyi Yang, Hua Wu, Fan Wang, Shuqi Sun

In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current turn are prone to be carried over to the next turn, causing error propagation. In this paper, we propose a novel Amendable Generation for Dialogue State Tracking (AG-DST), which contains a two-pass generation process: (1) generating a primitive dialogue state based on the dialogue of the current turn and the previous dialogue state, and (2) amending the primitive dialogue state from the first pass. With the additional amending generation pass, our model is tasked to learn more robust dialogue state tracking by amending the errors that still exist in the primitive dialogue state, which plays the role of reviser in the double-checking process and alleviates unnecessary error propagation. Experimental results show that AG-DST significantly outperforms previous works in two active DST datasets (MultiWOZ 2.2 and WOZ 2.0), achieving new state-of-the-art performances.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

PaddlePaddle/Knover officialpaddle report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dialogue State TrackingMulti-domain Dialogue State TrackingTask-Oriented Dialogue Systems

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Dialogue State Tracking Wizard-of-Oz AG-DST Joint 91.37 #1 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionAttention DropoutBPECosine AnnealingDSTDense ConnectionsDiscriminative Fine-TuningDropoutGPT-2Layer NormalizationLinear LayerLinear Warmup With Cosine AnnealingMulti-Head AttentionPLATO-2Residual ConnectionSoftmaxTransformerWeight Decay

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections