Papers › Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the...

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context

24 Nov 2019arXiv:1911.10484archive 2025-07-28

Yichi Zhang, Zhijian Ou, Zhou Yu

Conversations have an intrinsic one-to-many property, which means that multiple responses can be appropriate for the same dialog context. In task-oriented dialogs, this property leads to different valid dialog policies towards task completion. However, none of the existing task-oriented dialog generation approaches takes this property into account. We propose a Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses. Specifically, we first use dialog states to summarize the dialog history, and then discover all possible mappings from every dialog state to its different valid system actions. During dialog system training, we enable the current dialog state to map to all valid system actions discovered in the previous process to create additional state-action pairs. By incorporating these additional pairs, the dialog policy learns a balanced action distribution, which further guides the dialog model to generate diverse responses. Experimental results show that the proposed framework consistently improves dialog policy diversity, and results in improved response diversity and appropriateness. Our model obtains state-of-the-art results on MultiWOZ.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

gitlab.com/ucdavisnlp/damd-multiwoz officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
TonyNemo/UBAR-MultiWOZ mentioned on GitHubpytorchSyntology: not harvested report
bepoetree/mttod mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ACL Anthology id 2021.findings-emnlp.112 (that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
jasonyux/krls mentioned on GitHubpytorchSyntology: not harvested report
whatissimondoing/his-dialog mentioned on GitHubpytorchSyntology: not harvested report
yunhaoli1995/MAMD-TOD mentioned on GitHubpytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Data AugmentationDiversityEnd-To-End Dialogue Modelling

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
End-To-End Dialogue Modelling MULTIWOZ 2.0 DAMD BLEU 18.6 #6 of 6 Archive leaderboard report
End-To-End Dialogue Modelling MULTIWOZ 2.0 DAMD MultiWOZ (Inform) 76.3 #6 of 6 Archive leaderboard report
End-To-End Dialogue Modelling MULTIWOZ 2.0 DAMD MultiWOZ (Success) 60.4 #6 of 6 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.

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