Our new X account is live! Follow @wizwand_team for updates

Sentiment Analysis on IMDB (test)

97.42Accuracy

DV-ngrams-cosine + NB-weighted BON

Updated 3d ago

Evaluation Results

Method
DV-ngrams-cosine + NB-weighted BON 2022.05	97.42	-	-	-	-	-
LS-large 2021.07	96.8	-	-	-	-	-
SOTA 2024.06	96.68	-	-	-	-	-
roberta-large 2024.03	96.68	-	-	-	-	-
roberta-large 2024.03	96.54	-	-	-	-	-
RoBERTa-large 2021.07	96.5	-	-	-	-	-
Fine-tuning* 2023.05	96.4	-	-	-	-	-
LS-base 2021.07	96	-	-	-	-	-
DV-ngrams-cosine with NB sub-sampling + RoBERTa 2022.05	95.94	-	-	-	-	-
DV-ngrams-cosine + RoBERTa 2022.05	95.92	-	-	-	-	-
RoBERTa 2022.05	95.79	-	-	-	-	-
Longformer-base 2021.07	95.7	-	-	-	-	-
RoBERTa-base 2021.07	95.3	-	-	-	-	-
XLNet-Large 2021.06	95.3	-	-	-	-	-
roberta-base 2024.03	95.23	-	-	-	-	-
SENTECON 2023.05	95.1	-	-	-	-	-
MPNet 2023.05	95.1	-	-	-	-	-
bert-large 2024.03	95.03	-	-	-	-	-
SENTECON+ 2023.05	95	-	-	-	-	-
SENTECON+ 2023.05	95	-	-	-	-	-
roberta-large 2024.03	94.98	-	-	-	-	-
XLNet-Large 2021.06	94.9	-	-	-	-	-
SENTECON 2023.05	94.9	-	-	-	-	-
roberta-large 2024.03	94.83	-	-	-	-	-
UniMC* 2023.05	94.8	-	-	-	-	-
roberta-base 2024.03	94.74	-	-	-	-	-
CLINE 2021.07	94.5	-	-	-	-	-
bert-large 2024.03	94.29	-	-	-	-	-
roberta-base 2024.03	94.28	-	-	-	-	-
Virtual 2017.08	94.1	-	-	-	-	-
oh-LSTM 2017.08	94.1	-	-	-	-	-
ROBERTa-Large 2021.06	94.1	-	-	-	-	-
bert-large 2024.03	94.07	-	-	-	-	-
XLNet-Large 2021.06	93.9	-	-	-	-	-
TRNN 2017.08	93.8	-	-	-	-	-
BERT 2022.03	93.8	-	-	-	1	-
DV-ngrams-cosine + NB-weighted BON 2022.05	93.68	-	-	-	-	-
RoBERTa 2021.07	93.6	-	-	-	-	-
ROBERTa-Large 2021.06	93.6	-	-	-	-	-
UniMC (Rerun) 2023.05	93.6	-	-	-	-	-
roberta-base 2024.03	93.53	-	-	-	-	-
bert-base 2024.03	93.47	-	-	-	-	-
BERT-base 2019.10	93.46	-	-	-	-	-
ROBERTa-Large 2021.06	93.4	-	-	-	-	-
SSTuning-ALBERT 2023.05	93.4	-	-	-	-	-
DV-ngrams-cosine with NB sub-sampling 2022.05	93.36	-	-	-	-	-
bert-large 2024.03	93.31	-	-	-	-	-
Parallelized LMU 2021.02	93.2	-	-	-	-	-
TR-BERT 2022.03	93.2	-	-	-	2.9	-
DV-ngrams-cosine 2022.05	93.13	-	-	-	-	-
SSTuning-large 2023.05	93	-	-	-	-	-
Baseline BERT 2023.01	93	-	-	-	-	-
ContextFirst 2023.01	93	-	-	-	-	-
SparseQueries 2023.01	93	-	-	-	-	-
bmLSTM 2017.08	92.9	-	-	-	-	-
DistilBERT 2022.03	92.9	-	-	-	2	-
LSTM 2021.02	92.88	-	-	-	-	-
DistilBERT 2019.10	92.82	-	-	-	-	-
DistilBERT 2021.02	92.82	-	-	-	-	-
SA-LSTM 2017.08	92.8	-	-	-	-	-
bert-base 2024.03	92.76	-	-	-	-	-
Ensemble of RNNs and NB-SVM 2016.11	92.6	-	-	-	-	-
distilbert-base 2024.03	92.53	-	-	-	-	-
bert-base 2024.03	92.35	-	-	-	-	-
2 layer sequential BoW CNN 2016.11	92.3	-	-	-	-	-
BERT 2021.07	92.2	-	-	-	-	-
PoWER-BERT 2022.03	92.2	-	-	-	1.7	-
distilbert-base 2024.03	92.12	-	-	-	-	-
Funnel Transformer 2023.01	92	-	-	-	-	-
SparseQueries 2023.01	92	-	-	-	-	-
BCN+Char+CoVe 2017.08	91.8	-	-	-	-	-
WWM-BERT-Large 2021.06	91.8	-	-	-	-	-
AdapLeR 2022.03	91.7	-	-	-	3.21	-
ROBERTa-Large 2021.06	91.6	-	-	-	-	-
bert-base 2024.03	91.58	-	-	-	-	-
Densely-connected 4-layer QRNN 2016.11	91.4	-	-	150	-	-
NB-weighted BON 2022.05	91.29	-	-	-	-	-
distilbert-base 2024.03	91.23	-	-	-	-	-
NBSVM-bi 2016.11	91.2	-	-	-	-	-
WWM-BERT-Large 2021.06	91.2	-	-	-	-	-
Densely-connected 4-layer QRNN 2016.11	91.1	-	-	160	-	-
TE-MNLI 2023.05	91.1	-	-	-	-	-
WWM-BERT-Large 2021.06	91	-	-	-	-	-
SparseQueries 2023.01	91	-	-	-	-	-
SparseQueries 2023.01	91	-	-	-	-	-
Densely-connected 4-layer LSTM 2016.11	90.9	-	-	480	-	-
XLNet-Large 2021.06	90.8	-	-	-	-	-
distilbert-base 2024.03	90.77	-	-	-	-	-
BERT 2021.06	90.6	-	-	-	-	-
HyperPELT 2022.03	90.5	-	-	-	-	-
LKD+Init. 2023.05	90.4	-	-	-	-	-
LKD+Init. 2023.05	90.3	-	-	-	-	-
TE-MNLI 2023.05	90.2	-	-	-	-	-
Residual 2-layer bi-LSTM 2016.11	90.1	-	-	-	-	-
LSTM + CBA + LA 2018.11	90.1	-	-	-	-	-
LSTM with dynamic skip 2018.11	90.1	-	-	-	-	-
LSTM + CBA + LAG 2018.11	89.8	-	-	-	-	-
LSTM, fixed skip = 3 2018.11	89.6	-	-	-	-	-
LSTM + CBAG 2018.11	89.4	-	-	-	-	-
Jump LSTM 2018.11	89.4	-	-	-	-	-

Showing 100 of 269 rows