Latest

• A multi-task semantic decomposition framework with task-specific pre-training for few-shot ner
• APP：Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
• Continual Generalized Intent Discovery: Marching Towards Dynamic and Open-world Intent Recognition
• DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task
• Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT
• Revisit input perturbation problems for llms: A unified robustness evaluation framework for noisy slot filling task
• A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Named Entity Recognition
• Decoupling Pseudo Label Disambiguation and Representation Learning for Generalized Intent Discovery
• FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue
• Generative zero-shot prompt learning for cross-domain slot filling with inverse prompting
• Revisit Out-Of-Vocabulary Problem For Slot Filling: A Unified Contrastive Framework With Multi-Level Data Augmentations
• Seen to Unseen: Exploring Compositional Generalization of Multi-Attribute Controllable Dialogue Generation
• Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
• UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
• Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
• Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation
• Generalized Intent Discovery: Learning from Open World Dialogue System
• PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling
• ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge Disentanglement
• Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization
• Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold
• Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning
• A Finer-grain Universal Dialogue Semantic Structures based Model For Abstractive Dialogue Summarization
• Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion:Re-explore Zero-Shot Learning for Slot Filling
• Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
• Novel Slot Detection:A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System
• Scheduled Dialog Policy Learning:An Automatic Curriculum Learning Framework for Task-oriented Dialog System
• Adversarial Generative Distance-Based Classifier for Robust Out-of-Domain Detection
• Adversarial Self-Supervised Learning for Out-of-Domain Detection
• Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack
• Hierarchical Speaker-aware Sequence-to-sequence Model for Dialogue Summarization
• From context-aware:to knowledge-aware Boosting OOV tokens recognition in slot tagging with background knowledge
• Contrastive Zero-Shot Learning for Cross-Domain Slot Filling with Adversarial Attack
• A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space
• Adversarial Semantic Decoupling for Recognizing Open-Vocabulary Slots
• Learning Label-Relational Output Structure for Adaptive Sequence Labeling
• Adversarial Cross-Lingual Transfer Learning for Slot Tagging of Low-Resource Languages
• Learning to Tag OOV Tokens by Integrating Contextual Representation and Background Knowledge
• 一种基于结构化用户属性描述的个性化任务型对话系统
• 一种知识驱动的易配置任务导向型对话管理方法与系统
• 在线教育场景下的智能客服系统
• 多轮机票预订查询对话系统
• 学员培训模拟用户对话系统
• 智能语音质检系统
• 特定报修场景下的多轮对话系统
• 知识库问答系统