Natural Language Inference On Scitail

Metriken

Dev Accuracy

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

		Paper Title
MT-DNN-SMART_1%ofTrainingData	88.6	SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
Finetuned Transformer LM	-	Improving Language Understanding by Generative Pre-Training
RE2	-	Simple and Effective Text Matching with Richer Alignment Features
MT-DNN-SMARTLARGEv0	-	SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
SplitEE-S	-	SplitEE: Early Exit in Deep Neural Networks with Split Computing
CA-MTL	-	Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data
Hierarchical BiLSTM Max Pooling	-	Sentence Embeddings in NLI with Iterative Refinement Encoders
MT-DNN	-	Multi-Task Deep Neural Networks for Natural Language Understanding
MT-DNN-SMART_0.1%ofTrainingData	82.3	SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
MT-DNN-SMART_100%ofTrainingData	96.1	SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
CAFE	-	Compare, Compress and Propagate: Enhancing Neural Architectures with Alignment Factorization for Natural Language Inference
MT-DNN-SMART_10%ofTrainingData	91.3	SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization
Finetuned Transformer LM	-	-

0 of 13 row(s) selected.

Natural Language Inference On Scitail | SOTA | HyperAI