Share your thoughts, 1 month free Claude Pro on usSee more

Natural Language Inference on MultiNLI Mismatched

79.1Accuracy

Densely Interactive Inference Network

Updated 1mo ago

Evaluation Results

Method	Links
Densely Interactive Inference Network 2018.11		79.1
CAFE Ensemble 2017.12		79
CAFE 2017.12		77.9
Compare-Propagate Alignment-Factorized Encoders 2018.11		77.9
ESIM + Read 2017.12		77
ESIM 2017.12		75.8
CDME* 2018.04		74.9
Chen et al. 2018.11		74.9
Unweighted DME 2018.04		74.4
DME 2018.04		74.4
DME* 2018.04		74.3
CDME 2018.04		74.1
BiLSTM generalized pooling 2018.06		74
aESIM 2018.12		73.9
SSE 2018.04		73.6
Nie and Bansal 2018.11		73.6
BiLSTM gated-pooling 2018.06		73.6
Shortcut stacked BiLSTM 2018.06		73.6
ESIM 2018.12		73.5
Naive baseline 2018.04		73
BiLSTM max pooling 2018.06		73
Distance-Based Self-Attention Network 2018.11		72.9
Stacked Bi-LSTMs + shortcut connections + max-pooling 2018.11		72.2
ESIM 2017.12		72.1
Enhanced Sequential Inference Model 2018.11		71.9
BiLSTM last pooling 2018.06		71.9
BiLSTM mean pooling 2018.06		71.6
Directional Self-Attention Encoders 2018.11		71.4
Naive baseline 2018.04		71.1
Bi-LSTM sentence encoder + max-pooling 2018.11		71.1
Bi-LSTM sentence encoder + max-pooling + attention 2018.11		70.8
Stacked Bi-LSTMs + shortcut connections + max-pooling + attention 2018.11		70.5
Bi-LSTM sentence encoder + attention 2018.11		70.4
FastText BiLSTM-Max 2018.04		70.3
GloVe BiLSTM-Max 2018.04		70
Bi-GRU sentence encoder + attention 2018.11		69.5
BiLSTM 2017.12		69.4
Stacked Bi-GRUs + shortcut connections + max-pooling 2018.11		68.9
Stacked Bi-GRUs + shortcut connections + max-pooling + attention 2018.11		68.4
Bi-GRU sentence encoder + max-pooling + attention 2018.11		68.2
SWEM-max 2018.05		67.7
SWEM-concat 2018.05		67.6
Bi-GRU sentence encoder + max-pooling 2018.11		67.3
BiLSTM 2018.11		67.1
LSTM 2018.05		66.9
Bi-LSTM 2018.12		66.9
BiLSTM 2018.06		66.9
SWEM-aver 2018.05		66.2
CNN 2018.05		65.3
CBOW 2017.12		64.8
Continuous BOW (Averaging Word Embeddings) 2018.11		64.6
CBOW 2018.12		64.5
CBOW 2018.06		64.5
LaMini-GPT-J 2023.04		64
LaMini-LLaMA 2023.04		63.8
Alpaca 2023.04		39.6
GPT-J 2023.04		37.7
Majority 2017.12		35.6
Most Frequent Class 2018.11		35.6
LLaMA 2023.04		35.6