Intent Detection On Atis

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
Bi-model with decoder	98.99	A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling
Transformer-Capsule	98.89	Transformer-Capsule Model for Intent Detection
Attention Encoder-Decoder NN	98.43	Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
Joint model with recurrent slot label context	98.40	Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
CTRAN	98.07	CTRAN: CNN-Transformer-based Network for Natural Language Understanding
Joint BERT + CRF	97.9	BERT for Joint Intent Classification and Slot Filling
SF-ID (BLSTM) network	97.76	A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling
SF-ID	97.76	A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling
JointBERT-CAE	97.5	CAE: Mechanism to Diminish the Class Imbalanced in SLU Slot Filling Task
Stack-Propagation (+BERT)	97.50	A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding
Joint BERT	97.5	BERT for Joint Intent Classification and Slot Filling
DELTA (BLSTM-CRF)	97.40	DELTA: A DEep learning based Language Technology plAtform
AGIF	97.1	AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling
LIDSNet	95.97	LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network
Slot-Gated BLSTM with Attension	93.6	Slot-Gated Modeling for Joint Slot Filling and Intent Prediction
Capsule-NLU	0.95	Joint Slot Filling and Intent Detection via Capsule Neural Networks

0 of 16 row(s) selected.

Intent Detection On Atis | SOTA | HyperAI