def test_examine_model_weights(featurizer, vectorize, corpus, kb):
dataset = rel_ext.Dataset(corpus, kb)
splits = dataset.build_splits(
split_names=['tiny_train', 'tiny_dev', 'rest'],
split_fracs=[0.05, 0.05, 0.90],
seed=1)
results = rel_ext.experiment(splits,
train_split='tiny_train',
test_split='tiny_dev',
featurizers=[featurizer],
vectorize=vectorize,
verbose=False)
rel_ext.examine_model_weights(results)
solver='liblinear')
# In[12]:
baseline_results = rel_ext.experiment(splits,
train_split='train',
test_split='dev',
featurizers=featurizers,
model_factory=model_factory,
verbose=True)
# Studying model weights might yield insights:
# In[13]:
rel_ext.examine_model_weights(baseline_results)
# ### Distributed representations
#
# This simple baseline sums the GloVe vector representations for all of the words in the "middle" span and feeds those representations into the standard `LogisticRegression`-based `model_factory`. The crucial parameter that enables this is `vectorize=False`. This essentially says to `rel_ext.experiment` that your featurizer or your model will do the work of turning examples into vectors; in that case, `rel_ext.experiment` just organizes these representations by relation type.
# In[14]:
GLOVE_HOME = os.path.join('data', 'glove.6B')
# In[15]:
glove_lookup = utils.glove2dict(os.path.join(GLOVE_HOME, 'glove.6B.300d.txt'))
# In[16]: