Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention

Open paper
Benchmark Model Rank Results
natural-language-inference-on-snli600D (300+300) BiLSTM encoders with intra-attention and symbolic preproc.#51% Test Accuracy: 85.0% Train Accuracy: 85.9Parameters: 2.8m
natural-language-inference-on-snli600D (300+300) BiLSTM encoders with intra-attention#57% Test Accuracy: 84.2% Train Accuracy: 84.5Parameters: 2.8m
natural-language-inference-on-snli600D (300+300) BiLSTM encoders#61% Test Accuracy: 83.3% Train Accuracy: 86.4Parameters: 2.0m

Rank counts only results with a code link.