Accueil Actualités Articles de recherche récents Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Intent Detection On Mixsnips

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
GL-GIN	95.6	GL-GIN: Fast and Accurate Non-Autoregressive Model for Joint Multiple Intent Detection and Slot Filling
DGIF	97.8	A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding	-
SLIM	97.2	SLIM: Explicit Slot-Intent Mapping with BERT for Joint Multi-Intent Detection and Slot Filling
RoBERTa (PACL)	96.5	A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU	-
AGIF	96.5	AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
Co-guiding Net	97.7	Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs
BiSLU	97.8	Joint Multiple Intent Detection and Slot Filling with Supervised Contrastive Learning and Self-Distillation
SSRAN	98.4	A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding	-
SLIM (PACL)	96.9	A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU	-
Global Intent-Slot Co-occurence	95.5	Enhancing Joint Multiple Intent Detection and Slot Filling with Global Intent-Slot Co-occurrence
Uni-MIS	97.2	Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction
MISCA	97.3	MISCA: A Joint Model for Multiple Intent Detection and Slot Filling with Intent-Slot Co-Attention
Topic Information	96.3	Exploiting Topic Information for Joint Intent Detection and Slot Filling	-
TFMN (PACL)	97.4	A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLU	-
UGEN	96.9	Incorporating Instructional Prompts into a Unified Generative Framework for Joint Multiple Intent Detection and Slot Filling
TFMN	97.7	A Transformer-based Threshold-Free Framework for Multi-Intent NLU	-

0 of 16 row(s) selected.