Text Classification On Ag News

Metriken

Error

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
ToWE-SG	14.0	Task-oriented Word Embedding for Text Classification
Seq2CNN with GWS(50)	9.64	Abstractive Text Classification Using Sequence-to-convolution Neural Networks
Char-level CNN	9.51	Character-level Convolutional Networks for Text Classification
SVDCNN	9.45	Squeezed Very Deep Convolutional Neural Networks for Text Classification
VDCN	8.67	Very Deep Convolutional Networks for Text Classification
Balanced+bi-leaf-RNN	7.9	On Tree-Based Neural Sentence Modeling
CCCapsNet	7.61	Compositional Coding Capsule Network with K-Means Routing for Text Classification
LEAM	7.55	Joint Embedding of Words and Labels for Text Classification
fastText	7.5	Bag of Tricks for Efficient Text Classification
Capsule-B	7.4	Investigating Capsule Networks with Dynamic Routing for Text Classification
SWEM-concat	7.34	Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
EXAM	7	Explicit Interaction Model towards Text Classification
DPCNN	6.87	Deep Pyramid Convolutional Neural Networks for Text Categorization
CNN	6.57	Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings
ULMFiT (Small data)	6.3	Sampling Bias in Deep Active Classification: An Empirical Study
DNC+CUW	6.10	Learning to Remember More with Less Memorization
DRNN	5.53	Disconnected Recurrent Neural Networks for Text Categorization
ULMFiT	5.01	Universal Language Model Fine-tuning for Text Classification
L MIXED	4.95	Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function
BERT-ITPT-FiT	4.8	How to Fine-Tune BERT for Text Classification?

0 of 21 row(s) selected.

Command Palette

Text Classification On Ag News

Metriken

Ergebnisse