Sentiment Analysis On Sst 5 Fine Grained

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	Paper Title	Repository
Heinsen Routing + GPT-2	58.5	An Algorithm for Routing Capsules in All Domains
BP-Transformer + GloVe	52.71	BP-Transformer: Modelling Long-Range Context via Binary Partitioning	-
BCN+ELMo	54.7	Deep contextualized word representations
GloVe+Emo2Vec	43.6	Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
MPAD-path	49.68	Message Passing Attention Networks for Document Understanding	-
byte mLSTM7	54.6	A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors
Constituency Tree-LSTM	51.0	Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
C-LSTM	49.2	A C-LSTM Neural Network for Text Classification
RNTN	45.7	-	-
Heinsen Routing + RoBERTa Large	59.8	An Algorithm for Routing Vectors in Sequences
Epic	49.6	-	-
SWEM-concat	46.1	Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms
Joined Model Multi-tasking	44.82	Exploring Joint Neural Model for Sentence Level Discourse Parsing and Sentiment Analysis	-
MEAN	51.4	A Multi-sentiment-resource Enhanced Attention Network for Sentiment Classification	-
RoBERTa-large+Self-Explaining	59.1	Self-Explaining Structures Improve NLP Models
BCN+Char+CoVe	53.7	Learned in Translation: Contextualized Word Vectors
Bi-LSTM+2+5	50.4	Leveraging Multi-grained Sentiment Lexicon Information for Neural Sequence Models	-
CNN-RNF-LSTM	53.4	Convolutional Neural Networks with Recurrent Neural Filters
LM-CPPF RoBERTa-base	54.9	LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning
Bi-CAS-LSTM	53.6	Cell-aware Stacked LSTMs for Modeling Sentences	-

0 of 29 row(s) selected.