Awesome
Decomposable-Attention
A Tensorflow implementation of Parikh's A Decomposable Attention Model for Natural Language Inference from EMNLP 2016.
Dataset
The dataset used for this task is Stanford Natural Language Inference (SNLI). Pretrained GloVe embeddings obtained from common crawl with 840B tokens used for words.
Requirements
- Python>=3
- NumPy
- TensorFlow>=1.8
Usage
Download dataset from Stanford Natural Language Inference, then move snli_1.0_train.jsonl
, snli_1.0_dev.jsonl
, snli_1.0_test.jsonl
into ./SNLI/raw data
.
# move dataset to the right place
mkdir -p ./SNLI/raw\ data
mv snli_1.0_*.jsonl ./SNLI/raw\ data
Data preprocessing for convert source data into an easy-to-use format.
python3 Utils.py
Default hyper-parameters have been stored in config file in the path of ./config/config.yaml
.
Training model:
python3 Train.py
Test model:
python3 Test.py
Results
Decomposable Attention | Reported | Our Experiments |
---|---|---|
Accuracy | 86.3% | 85.4% |