Sentiment Analysis On Sst 2 Binary

Métriques

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Accuracy	Paper Title	Repository
CNN	91.2	On the Role of Text Preprocessing in Neural Network Architectures: An Evaluation Study on Text Categorization and Sentiment Analysis
SpanBERT	94.8	SpanBERT: Improving Pre-training by Representing and Predicting Spans
MV-RNN	82.9	-	-
gMLP-large	94.8	Pay Attention to MLPs
C-LSTM	87.8	A C-LSTM Neural Network for Text Classification
ASA + BERT-base	94.1	Adversarial Self-Attention for Language Understanding
Emo2Vec	81.2	Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
ASA + RoBERTa	96.3	Adversarial Self-Attention for Language Understanding
Single layer bilstm distilled from BERT	90.7	Distilling Task-Specific Knowledge from BERT into Simple Neural Networks
SMART+BERT-BASE	93	SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
USE_T+CNN (lrn w.e.)	87.21	Universal Sentence Encoder
MPAD-path	87.75	Message Passing Attention Networks for Document Understanding	-
CNN-multichannel [kim2013]	88.1	Convolutional Neural Networks for Sentence Classification
T5-11B	97.5	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
24hBERT	93.0	How to Train BERT with an Academic Budget
RealFormer	94.04	RealFormer: Transformer Likes Residual Attention
T5-3B	97.4	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
T5-Large 770M	96.3	Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
2-layer LSTM [tai2015improved]	86.3	Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
BLSTM-2DCNN	89.5	Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling

0 of 88 row(s) selected.