Papers with Code 아카이브
Dialogue State Tracking
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 7
- 보존된 평가 기록
- 39
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.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Approaching Dialogue State Tracking via Aligning Speech Encoders and LLMs
Factors affecting the in-context learning abilities of LLMs for dialogue state tracking
Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs
Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings
Enhancing LLM Reliability via Explicit Knowledge Boundary Modeling
Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling
Intent-driven In-context Learning for Few-shot Dialogue State Tracking
Schema Augmentation for Zero-Shot Domain Adaptation in Dialogue State Tracking
Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot
CorrectionLM: Self-Corrections with SLM for Dialogue State Tracking
A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
Confidence Estimation for LLM-Based Dialogue State Tracking
Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
Keyword-Aware ASR Error Augmentation for Robust Dialogue State Tracking
Continual Dialogue State Tracking via Reason-of-Select Distillation
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
Multi-Modal Dialogue State Tracking for Playing GuessWhich Game
Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations
Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation
Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4
An Approach to Build Zero-Shot Slot-Filling System for Industry-Grade Conversational Assistants
Plan, Generate and Complicate: Improving Low-resource Dialogue State Tracking via Easy-to-Difficult Zero-shot Data Augmentation
Making Task-Oriented Dialogue Datasets More Natural by Synthetically Generating Indirect User Requests
Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents
Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Tracking
Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation
Many Hands Make Light Work: Task-Oriented Dialogue System with Module-Based Mixture-of-Experts
Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models
MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking
Common Ground Tracking in Multimodal Dialogue
JMultiWOZ: A Large-Scale Japanese Multi-Domain Task-Oriented Dialogue Dataset
Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks
Granular Change Accuracy: A More Accurate Performance Metric for Dialogue State Tracking
Chain of Thought Explanation for Dialogue State Tracking
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.