https://github.com/willyhc22/instructtods
공식 코드InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems
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.
InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems
Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection
How to Build User Simulators to Train RL-based Dialog Systems
SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks
Self-training with Two-phase Self-augmentation for Few-shot Dialogue Generation
Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models
SeqDialN: Sequential Visual Dialog Networks in Joint Visual-Linguistic Representation Space
An animated picture says at least a thousand words: Selecting Gif-based Replies in Multimodal Dialog
MidMed: Towards Mixed-Type Dialogues for Medical Consultation
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes
Multi-Modal Dialogue State Tracking for Playing GuessWhich Game
Context-Sensitive Generation Network for Handing Unknown Slot Values in Dialogue State Tracking
ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
LiveLongBench: Tackling Long-Context Understanding for Spoken Texts from Live Streams
Robust Unstructured Knowledge Access in Conversational Dialogue with ASR Errors
A Survey on Spoken Language Understanding: Recent Advances and New Frontiers
Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
Multi-User MultiWOZ: Task-Oriented Dialogues among Multiple Users
Bridging Cultural Nuances in Dialogue Agents through Cultural Value Surveys
Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking
Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory
Concept Matching with Agent for Out-of-Distribution Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.