Browse > Natural Language Processing > Dialogue > Dialogue State Tracking

Dialogue State Tracking

30 papers with code · Natural Language Processing
Subtask of Dialogue

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.

Leaderboards

Latest papers with code

A Simple Language Model for Task-Oriented Dialogue

2 May 2020budzianowski/multiwoz

Task-oriented dialogue is often decomposed into three tasks: understanding user input, deciding actions, and generating a response.

DIALOGUE STATE TRACKING LANGUAGE MODELLING TRANSFER LEARNING

217
02 May 2020

ToD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogues

15 Apr 2020jasonwu0731/ToD-BERT

The use of pre-trained language models has emerged as a promising direction for improving dialogue systems.

DIALOGUE STATE TRACKING LANGUAGE MODELLING NATURAL LANGUAGE UNDERSTANDING

13
15 Apr 2020

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

27 Feb 2020sz128/NLU_DST_datasets

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.

DIALOGUE STATE TRACKING TASK-ORIENTED DIALOGUE SYSTEMS

50
27 Feb 2020

Non-Autoregressive Dialog State Tracking

ICLR 2020 henryhungle/NADST

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.

DIALOGUE STATE TRACKING MULTI-DOMAIN DIALOGUE STATE TRACKING

22
19 Feb 2020

Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks

3 Feb 2020kolk/MODELING-ASR-AMBIGUITY-FOR-NEURAL-DIALOGUE-STATE-TRACKING-USING-WORD-CONFUSION-NETWORKS

Spoken dialogue systems typically use a list of top-N ASR hypotheses for inferring the semantic meaning and tracking the state of the dialogue.

DIALOGUE STATE TRACKING SPOKEN DIALOGUE SYSTEMS

0
03 Feb 2020

Schema-Guided Dialogue State Tracking Task at DSTC8

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

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.

DATA AUGMENTATION DIALOGUE STATE TRACKING

205
02 Feb 2020

Visual Dialogue State Tracking for Question Generation

12 Nov 2019xubuvd/guesswhat

A visual dialogue state is defined as the distribution on objects in the image as well as representations of objects.

DIALOGUE STATE TRACKING QUESTION GENERATION VISUAL DIALOG

5
12 Nov 2019

Scalable Neural Dialogue State Tracking

22 Oct 2019vevake/GSAT

A Dialogue State Tracker (DST) is a key component in a dialogue system aiming at estimating the beliefs of possible user goals at each dialogue turn.

DIALOGUE STATE TRACKING

3
22 Oct 2019

Domain Transfer in Dialogue Systems without Turn-Level Supervision

16 Sep 2019coastalcph/dialog-rl

Task oriented dialogue systems rely heavily on specialized dialogue state tracking (DST) modules for dynamically predicting user intent throughout the conversation.

DIALOGUE STATE TRACKING TASK-ORIENTED DIALOGUE SYSTEMS

1
16 Sep 2019