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

JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset

nu-dialogue/jmultiwoz 26 Mar 2024

In this study, towards the advancement of research and development of task-oriented dialogue systems in Japanese, we constructed JMultiWOZ, the first Japanese language large-scale multi-domain task-oriented dialogue dataset.

12
26 Mar 2024

Common Ground Tracking in Multimodal Dialogue

csu-signal/Common-Ground-detection 26 Mar 2024

Within Dialogue Modeling research in AI and NLP, considerable attention has been spent on ``dialogue state tracking'' (DST), which is the ability to update the representations of the speaker's needs at each turn in the dialogue by taking into account the past dialogue moves and history.

0
26 Mar 2024

Encode Once and Decode in Parallel: Efficient Transformer Decoding

boru-roylu/encode-once-and-decode-in-parallel 19 Mar 2024

Transformer-based NLP models are powerful but have high computational costs that limit deployment scenarios.

4
19 Mar 2024

State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Tracking

sleepwalkerg/svag 30 Jan 2024

Experimental results on the MultiWOZ 2. 1 dataset show that our method which has only less than 1 billion parameters achieves state-of-the-art performance under the data ratio settings of 5%, 10%, and 25% when limited to models under 100 billion parameters.

0
30 Jan 2024

Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Tracking

jihyunlee1/e2e-dst 4 Dec 2023

We address this by investigating synthetic audio data for audio-based DST.

6
04 Dec 2023

Detecting agreement in multi-party dialogue: evaluating speaker diarisation versus a procedural baseline to enhance user engagement

ddenley/multi-person-quiz 6 Nov 2023

Conversational agents participating in multi-party interactions face significant challenges in dialogue state tracking, since the identity of the speaker adds significant contextual meaning.

1
06 Nov 2023

Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users

yohanjo/multiuser_multiwoz 31 Oct 2023

While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected to communicate with multiple users simultaneously who make decisions collaboratively.

3
31 Oct 2023

Towards LLM-driven Dialogue State Tracking

woodscene/ldst 23 Oct 2023

In this study, we conduct an initial examination of ChatGPT's capabilities in DST.

23
23 Oct 2023

Turn-Level Active Learning for Dialogue State Tracking

hyintell/al-dst 23 Oct 2023

Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems.

0
23 Oct 2023

UNO-DST: Leveraging Unlabelled Data in Zero-Shot Dialogue State Tracking

lichuangnus/uno-dst 16 Oct 2023

Previous zero-shot dialogue state tracking (DST) methods only apply transfer learning, but ignore unlabelled data in the target domain.

4
16 Oct 2023