Dialogue Systems
Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators
·2252 words·11 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Dialogue Systems
🏢 Baichuan Inc.
AI-powered medical consultations often struggle with the inquiry phase. This paper presents a novel patient simulator trained on real interactions, revealing that effective inquiry significantly impac…
Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding
·2127 words·10 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Dialogue Systems
🏢 Peking University
Friends-MMC: A new dataset facilitates multi-modal multi-party conversation understanding by providing 24,000+ utterances with video, audio, and speaker annotations, enabling advancements in character…
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
·2286 words·11 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Dialogue Systems
🏢 School of Artificial Intelligence, University of Chinese Academy of Sciences
DEMO benchmark revolutionizes dialogue modeling by focusing on fine-grained elements (Prelude, Interlocution, Epilogue), enabling comprehensive evaluation and superior agent performance.
Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use
·3802 words·18 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Dialogue Systems
🏢 University of Michigan
Teaching AI agents with diverse and informative language feedback dramatically improves their learning, generalization, and adaptability.
A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents
·2316 words·11 mins·
loading
·
loading
AI Generated
🤗 Daily Papers
Natural Language Processing
Dialogue Systems
🏢 Computer Science and Engineering Department, IIT Kharagpur
This research introduces MLMCID, a novel pointer network architecture that excels at jointly extracting multiple intent spans and detecting multi-label, multi-class intents from complex, multilingual …