DR-BiLSTM: Dependent Reading Bidirectional LSTM for Natural Language Inference

We present a novel deep learning architecture to address the natural language inference (NLI) task. Existing approaches mostly rely on simple reading mechanisms for independent encoding of the premise and hypothesis... (read more)

PDF Abstract NAACL 2018 PDF NAACL 2018 Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Natural Language Inference SNLI 450D DR-BiLSTM % Test Accuracy 88.5 # 17
% Train Accuracy 94.1 # 15
Parameters 7.5m # 3
Natural Language Inference SNLI 450D DR-BiLSTM Ensemble % Test Accuracy 89.3 # 11
% Train Accuracy 94.8 # 12
Parameters 45m # 3

Methods used in the Paper


METHOD TYPE
Sigmoid Activation
Activation Functions
Tanh Activation
Activation Functions
LSTM
Recurrent Neural Networks