Gupta et al. (2020)#
Publication#
Repositories#
https://github.com/nitishgupta/nmn-drop
Available Models#
-
Description: A model which uses neural module networks to answer questions on the DROP dataset
Name:
gupta2020-nmn
Usage:
from repro.models.gupta2020 import NeuralModuleNetwork model = NeuralModuleNetwork() answer = model.predict("context paragraph", "question")
Implementation Notes#
The implementation here was based on the instructions in the original repository.
Docker Information#
Image name:
gupta2020
Docker Hub: https://hub.docker.com/repository/docker/danieldeutsch/gupta2020
Build command:
repro setup gupta2020 [--silent]
Requires network: No
Testing#
repro setup gupta2020
pytest models/gupta2020/tests
Status#
[x] Regression unit tests pass
[x] Correctness unit tests pass
The unit tests check to make sure the model returns the same answers for a few examples in their demo. Latest successful test on Github.[ ] Model runs on full test dataset
Not tested[ ] Predictions approximately replicate results reported in the paper
Not tested[ ] Predictions exactly replicate results reported in the paper
Not tested