https://github.com/facebookresearch/dst-egqa
공식 코드Continual Dialogue State Tracking via Example-Guided Question Answering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Dialogue is notoriously hard to evaluate. Past approaches have used human evaluation.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Continual Dialogue State Tracking via Example-Guided Question Answering
Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions
KnowPrefix-Tuning: A Two-Stage Prefix-Tuning Framework for Knowledge-Grounded Dialogue Generation
Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding
CAB: Empathetic Dialogue Generation with Cognition, Affection and Behavior
A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
Improvement of a dedicated model for open domain persona-aware dialogue generation
Dual Attention Networks for Visual Reference Resolution in Visual Dialog
The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training
Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer
Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking
An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation
Graph-Evolving Meta-Learning for Low-Resource Medical Dialogue Generation
CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling
Lift Yourself Up: Retrieval-augmented Text Generation with Self Memory
Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge
XQA-DST: Multi-Domain and Multi-Lingual Dialogue State Tracking
Benchmarking Commercial Intent Detection Services with Practice-Driven Evaluations
Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations
Learning from Easy to Complex: Adaptive Multi-curricula Learning for Neural Dialogue Generation
Group-wise Contrastive Learning for Neural Dialogue Generation
Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems
UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues
WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.