Dialogue State Tracking

123 papers with code • 7 benchmarks • 11 datasets

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.

Libraries

Use these libraries to find Dialogue State Tracking models and implementations

Most implemented papers

Global-Locally Self-Attentive Dialogue State Tracker

salesforce/glad 19 May 2018

Dialogue state tracking, which estimates user goals and requests given the dialogue context, is an essential part of task-oriented dialogue systems.

Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation

AuCson/SEDST 31 Aug 2018

However, the \emph{expensive nature of state labeling} and the \emph{weak interpretability} make the dialogue state tracking a challenging problem for both task-oriented and non-task-oriented dialogue generation: For generating responses in task-oriented dialogues, state tracking is usually learned from manually annotated corpora, where the human annotation is expensive for training; for generating responses in non-task-oriented dialogues, most of existing work neglects the explicit state tracking due to the unlimited number of dialogue states.

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

jasonwu0731/trade-dst ACL 2019

Over-dependence on domain ontology and lack of knowledge sharing across domains are two practical and yet less studied problems of dialogue state tracking.

Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering

alexa/dstqa 7 Nov 2019

Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems.

Schema-Guided Dialogue State Tracking Task at DSTC8

google-research-datasets/dstc8-schema-guided-dialogue 2 Feb 2020

The goal of this task is to develop dialogue state tracking models suitable for large-scale virtual assistants, with a focus on data-efficient joint modeling across domains and zero-shot generalization to new APIs.

CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

thu-coai/CrossWOZ TACL 2020

To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset.

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 24 Oct 2020

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.

Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing

huybery/r2sql 5 Jan 2021

Semantic parsing has long been a fundamental problem in natural language processing.

Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking

facebookresearch/Zero-Shot-DST 10 May 2021

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data.