https://github.com/AlibabaResearch/DAMO-ConvAI/tree/main/pace
공식 코드PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
Parallel Interactive Networks for Multi-Domain Dialogue State Generation
Neural Dialogue State Tracking with Temporally Expressive Networks
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding
A Two-dimensional Zero-shot Dialogue State Tracking Evaluation Method using GPT-4
Continual Dialogue State Tracking via Reason-of-Select Distillation
TaSL: Continual Dialog State Tracking via Task Skill Localization and Consolidation
An Empirical Study of Cross-Lingual Transferability in Generative Dialogue State Tracker
Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models
Structured Prediction as Translation between Augmented Natural Languages
Diable: Efficient Dialogue State Tracking as Operations on Tables
Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System
Efficient Encoder-Decoder Transformer Decoding for Decomposable Tasks
Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources
DeepStruct: Pretraining of Language Models for Structure Prediction
Dialogue State Tracking with a Language Model using Schema-Driven Prompting
Efficient Dialogue State Tracking by Selectively Overwriting Memory
Domain Transfer in Dialogue Systems without Turn-Level Supervision
Prompter: Zero-shot Adaptive Prefixes for Dialogue State Tracking Domain Adaptation
Beyond Ontology in Dialogue State Tracking for Goal-Oriented Chatbot
Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking
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
A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.