Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference

Open paper
Benchmark Model Rank Results
natural-language-inference-on-snli300D DMAN Ensemble#12% Test Accuracy: 89.6% Train Accuracy: 96.1Parameters: 79m
natural-language-inference-on-snli300D DMAN#18% Test Accuracy: 88.8% Train Accuracy: 95.4Parameters: 9.2m

Rank counts only results with a code link.