SOTAVerified

Dialogue State Tracking

Dialogue state tacking consists of determining at each turn of a dialogue the full representation of what the user wants at that point in the dialogue, which contains a goal constraint, a set of requested slots, and the user's dialogue act.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 121–130 of 300 papers

TitleStatusHype
Choice Fusion as Knowledge for Zero-Shot Dialogue State TrackingCode0
Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Tracking—0
Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking—0
Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning—0
KILDST: Effective Knowledge-Integrated Learning for Dialogue State Tracking using Gazetteer and Speaker Information—0
Extrinsic Evaluation of Machine Translation Metrics—0
DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning—0
Self-Training with Purpose Preserving Augmentation Improves Few-shot Generative Dialogue State Tracking—0
MoNET: Tackle State Momentum via Noise-Enhanced Training for Dialogue State Tracking—0
MetaASSIST: Robust Dialogue State Tracking with Meta LearningCode0
Show:102550
← PrevPage 13 of 30Next →

No leaderboard results yet.