Enhanced LSTM for Natural Language Inference

Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging... (read more)

PDF Abstract ACL 2017 PDF ACL 2017 Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Natural Language Inference SNLI 600D ESIM + 300D Syntactic TreeLSTM % Test Accuracy 88.6 # 26
% Train Accuracy 93.5 # 21
Parameters 7.7m # 3

Results from Other Papers


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK SOURCE PAPER COMPARE
Natural Language Inference SNLI Enhanced Sequential Inference Model (Chen et al., [2017a]) % Test Accuracy 88.0 # 35

Methods used in the Paper


METHOD TYPE
ESIM
Sequence To Sequence Models