Papers with Code 아카이브
Dialogue
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 21
- 평가표
- 1
- 보존된 평가 기록
- 1
Dialogue is notoriously hard to evaluate. Past approaches have used human evaluation.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding
Policy-driven Knowledge Selection and Response Generation for Document-grounded Dialogue
DM-Codec: Distilling Multimodal Representations for Speech Tokenization
MediTOD: An English Dialogue Dataset for Medical History Taking with Comprehensive Annotations
On the Use of Audio to Improve Dialogue Policies
From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation
Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants
A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment Analysis
Sylber: Syllabic Embedding Representation of Speech from Raw Audio
Listening to Patients: A Framework of Detecting and Mitigating Patient Misreport for Medical Dialogue Generation
SyllableLM: Learning Coarse Semantic Units for Speech Language Models
PersoBench: Benchmarking Personalized Response Generation in Large Language Models
MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
Intent Detection in the Age of LLMs
A Two-Stage Proactive Dialogue Generator for Efficient Clinical Information Collection Using Large Language Model
AfriHuBERT: A self-supervised speech representation model for African languages
Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking
Experimental Evaluation of Machine Learning Models for Goal-oriented Customer Service Chatbot with Pipeline Architecture
Minimizing Live Experiments in Recommender Systems: User Simulation to Evaluate Preference Elicitation Policies
Speech Recognition Rescoring with Large Speech-Text Foundation Models
DiaSynth: Synthetic Dialogue Generation Framework for Low Resource Dialogue Applications
A Zero-Shot Open-Vocabulary Pipeline for Dialogue Understanding
MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation
MultiMed: Multilingual Medical Speech Recognition via Attention Encoder Decoder
LLMR: Knowledge Distillation with a Large Language Model-Induced Reward
Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection
Increasing faithfulness in human-human dialog summarization with Spoken Language Understanding tasks
Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT
ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework
Confidence Estimation for LLM-Based Dialogue State Tracking
Clean Label Attacks against SLU Systems
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
UPCS: Unbiased Persona Construction for Dialogue Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.