Multi-domain Dialogue State Tracking

29 papers with code • 6 benchmarks • 2 datasets

This task has no description! Would you like to contribute one?

Libraries

Use these libraries to find Multi-domain Dialogue State Tracking models and implementations

Latest papers with no code

Schema Graph-Guided Prompt for Multi-Domain Dialogue State Tracking

no code yet • 10 Nov 2023

Tracking dialogue states is an essential topic in task-oriented dialogue systems, which involve filling in the necessary information in pre-defined slots corresponding to a schema.

Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking

no code yet • ACL 2022

Existing approaches that have considered such relations generally fall short in: (1) fusing prior slot-domain membership relations and dialogue-aware dynamic slot relations explicitly, and (2) generalizing to unseen domains.

Dynamic Schema Graph Fusion Network for Multi-Domain Dialogue State Tracking

no code yet • ACL ARR November 2021

Existing approaches that have considered such relations generally fall short in: (1) fusing prior slot-domain membership relations and dialogue-aware dynamic slot relations explicitly, and (2) generalizing to unseen domains.

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialogue State Tracking

no code yet • ACL 2021

Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking

no code yet • 1 Jun 2021

Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.

SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing

no code yet • NeurIPS Workshop CAP 2020

Conversational Semantic Parsing (CSP) is the task of converting a sequence of natural language queries to formal language (e. g., SQL, SPARQL) that can be executed against a structured ontology (e. g. databases, knowledge bases).

Domain-slot Relationship Modeling using a Pre-trained Language Encoder for Multi-Domain Dialogue State Tracking

no code yet • 1 Jan 2021

We propose a model for multi-domain dialogue state tracking that effectively models the relationship among domain-slot pairs using a pre-trained language encoder.

GCDST: A Graph-based and Copy-augmented Multi-domain Dialogue State Tracking

no code yet • Findings of the Association for Computational Linguistics 2020

As an essential component of task-oriented dialogue systems, Dialogue State Tracking (DST) takes charge of estimating user intentions and requests in dialogue contexts and extracting substantial goals (states) from user utterances to help the downstream modules to determine the next actions of dialogue systems.

Multi-Domain Dialogue State Tracking based on State Graph

no code yet • 21 Oct 2020

Existing approaches usually concatenate previous dialogue state with dialogue history as the input to a bi-directional Transformer encoder.

The SPPD System for Schema Guided Dialogue State Tracking Challenge

no code yet • 16 Jun 2020

This paper introduces one of our group's work on the Dialog System Technology Challenges 8 (DSTC8), the SPPD system for Schema Guided dialogue state tracking challenge.