Multi-domain Dialogue State Tracking
29 papers with code • 6 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in Multi-domain Dialogue State Tracking
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Multi-domain Dialogue State Tracking models and implementations
MultiWOZ
SGD
Latest papers
CoCo: Controllable Counterfactuals for Evaluating Dialogue State Trackers
salesforce/coco-dst
•
•
ICLR 2021
Dialogue state trackers have made significant progress on benchmark datasets, but their generalization capability to novel and realistic scenarios beyond the held-out conversations is less understood.
Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking
zengyan-97/Transformer-DST
•
•
However, in such a stacked encoder-decoder structure, the operation prediction objective only affects the BERT encoder and the value generation objective mainly affects the RNN decoder.
DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue
alexa/dialoglue
•
•
A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains.
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
In this paper, we propose Minimalist Transfer Learning (MinTL) to simplify the system design process of task-oriented dialogue systems and alleviate the over-dependency on annotated data.
Parallel Interactive Networks for Multi-Domain Dialogue State Generation
BDBC-KG-NLP/PIN_EMNLP2020
•
•
EMNLP 2020
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.
A Simple Language Model for Task-Oriented Dialogue
salesforce/simpletod
•
•
NeurIPS 2020
Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response.
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
We show that data augmentation through synthesized data can improve the accuracy of zero-shot learning for both the TRADE model and the BERT-based SUMBT model on the MultiWOZ 2. 1 dataset.
Non-Autoregressive Dialog State Tracking
henryhungle/NADST
•
•
ICLR 2020
Recent efforts in Dialogue State Tracking (DST) for task-oriented dialogues have progressed toward open-vocabulary or generation-based approaches where the models can generate slot value candidates from the dialogue history itself.
Efficient Dialogue State Tracking by Selectively Overwriting Memory
This mechanism consists of two steps: (1) predicting state operation on each of the memory slots, and (2) overwriting the memory with new values, of which only a few are generated according to the predicted state operations.
Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
alexa/dstqa
•
•
Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems.
