https://github.com/abendayan/attention
https://github.com/abendayan/attention
attention-model deep-learning dynet
Last synced: 9 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/abendayan/attention
- Owner: abendayan
- Created: 2018-01-27T17:31:46.000Z (over 8 years ago)
- Default Branch: master
- Last Pushed: 2018-06-03T19:59:24.000Z (about 8 years ago)
- Last Synced: 2025-03-02T08:33:24.327Z (over 1 year ago)
- Topics: attention-model, deep-learning, dynet
- Language: Python
- Size: 6.84 KB
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
##A Decomposable Attention Model for Natural Language Inference
This is an adaptation in dynet of the model presented in https://arxiv.org/pdf/1606.01933v1.pdf
I used the glove.42B.300d.txt.
Download them from: http://nlp.stanford.edu/data/glove.42B.300d.zip
To run the model, I put the glove's words and the snli data in a folder named data.
If they are in an other folder, give the correct path in the config.py file.
To run, use the command:
python model.py
It is recommended to run with autobatch enabled:
python model.py --dynet-autobatch 1