Dialogue State Tracking
7개 벤치마크 · 논문 311편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
Language Models are Unsupervised Multitask Learners
MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines
KLUE: Korean Language Understanding Evaluation
Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset
Papers
Candidate Attended Dialogue State Tracking Using BERT
Dialogue state tracking (DST) is one of the core components in task-oriented dialogue systems. At each turn in a conversation, DST estimates the user belief or dialogue state, which is used as input for downstream module…
Task-Oriented Dialogue SystemsZero-shot GeneralizationDialogue State TrackingSTREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media
Large language models for vertical domains are bottlenecked by the scarcity of complex, domain-specific task-oriented dialogues. Existing data acquisition pipelines face a persistent trilemma: expert annotation is expens…
Dialogue State TrackingReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking
Task-oriented dialogue systems -- handling transactions, reservations, and service requests -- require predictable behavior, yet the moderately-sized LLMs needed for practical latency are prone to hallucination and forma…
Task-Oriented Dialogue SystemsDialogue State TrackingMultimodal Hidden Markov Models for Persistent Emotional State Tracking
Tracking an interpretable emotional arc of a conversation via the sentiment of individual utterances processed as a whole is central to both understanding and guiding communication in applied, especially clinical, conver…
Dialogue State TrackingEmotion RecognitionGEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite their impressive general capabilities. We pr…
Computational EfficiencyDialogue State TrackingGraph Neural NetworkDynamic Knowledge Fusion for Multi-Domain Dialogue State Tracking
The performance of task-oriented dialogue models is strongly tied to how well they track dialogue states, which records and updates user information across multi-turn interactions. However, current multi-domain DST encou…
Dialogue State TrackingContrastive Learning