A Decomposable Attention Model for Natural Language Inference

Benchmark Model Rank Results
natural-language-inference-on-snli200D decomposable attention feed-forward model with intra-sentence attention#31% Test Accuracy: 86.8% Train Accuracy: 90.5Parameters: 580k
natural-language-inference-on-snli200D decomposable attention model with intra-sentence attention#32% Test Accuracy: 86.8% Train Accuracy: 90.5Parameters: 580k
natural-language-inference-on-snli200D decomposable attention feed-forward model#38% Test Accuracy: 86.3% Train Accuracy: 89.5Parameters: 380k
natural-language-inference-on-snli200D decomposable attention model#39% Test Accuracy: 86.3% Train Accuracy: 89.5Parameters: 380k