Stochastic Answer Networks for Natural Language Inference

Understand

We propose a stochastic answer network (SAN) to explore multi-step inference strategies in Natural Language Inference.

• Rather than directly predicting the results given the inputs, the model maintains a state and iteratively refines its predictions.
• Our experiments show that SAN achieves the state-of-the-art results on three benchmarks: Stanford Natural Language Inference (SNLI) dataset, MultiGenre Natural Language Inference (MultiNLI) dataset and Quora Question Pairs dataset.