bioasq-rl

Experiments using Reinforcement Learning for BioASQ

Train and evaluate reinforce for debugging

$ python3
>>> import rl
>>> rl.DEBUG = True
>>> from rl import reinforce
>>> reinforce.train()

>>> from rl import reinforce
>>> reinforce.train()

$ python3
>>> import rl
>>> rl.DEBUG = True
>>> from rl import reinforce
>>> reinforce.NNbaseline()

$ python3
>>> from rl import reinforce
>>> reinforce.NNbaseline()

$ python3
>>> from rl import reinforce
>>> reinforce.baseline()

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
rl		rl
BioASQ-trainingDataset5b.json		BioASQ-trainingDataset5b.json
LICENSE		LICENSE
README.md		README.md
my_tokenizer.py		my_tokenizer.py
rl-rouge5b.csv		rl-rouge5b.csv