Stochastic Answer Networks for Natural Language Inference

21 Apr 2018Xiaodong LiuKevin DuhJianfeng Gao

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... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Natural Language Inference SNLI Stochastic Answer Network % Test Accuracy 88.5 # 15
% Train Accuracy 93.3 # 19
Parameters 3.5m # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet