def get_sentence_importance_scores(embedding_model, logistic_regression, x):
objective = CrossEntropy()
x_combined = [w for s in x for w in s]
meta_combined = {
'lengths': np.asarray([len(x_combined)]),
'space_below': cpu.space.CPUSpace(
axes=('b', 'w'),
extents={'b': 1, 'w': len(x_combined)})
}
x_combined = np.asarray(x_combined).reshape((1, -1))
embeddings, embeddings_meta, embeddings_state = embedding_model.fprop(
x_combined, meta=dict(meta_combined), return_state=True)
embeddings_meta['space_below'] = embeddings_meta['space_above']
y_hat, y_hat_meta, log_reg_state = logistic_regression.fprop(
embeddings, meta=dict(embeddings_meta), return_state=True)
y_hat_meta['space_below'] = y_hat_meta['space_above']
loss, loss_meta, loss_state = objective.fprop(
y_hat, max_error_label(y_hat), meta=dict(y_hat_meta))
delta, delta_meta = objective.bprop(
y_hat, max_error_label(y_hat), meta=dict(loss_meta), fprop_state=loss_state)
delta = logistic_regression.bprop(
delta, meta=dict(delta_meta), fprop_state=log_reg_state)
C = combiner_matrix(map(len, x))
sentence_delta = np.dot(delta, C)
sentence_embedding = np.dot(embeddings, C)
# normalize for cosine distance
sentence_delta /= np.sqrt(np.sum(sentence_delta**2, axis=1, keepdims=True))
sentence_embedding /= np.sqrt(np.sum(sentence_embedding**2, axis=1, keepdims=True))
sentence_importance_scores = np.abs(np.sum(sentence_delta * sentence_embedding, axis=0))
return sentence_importance_scores
def get_sentence_importance_scores(embedding_model, logistic_regression, x):
objective = CrossEntropy()
x_combined = [w for s in x for w in s]
meta_combined = {
"lengths": np.asarray([len(x_combined)]),
"space_below": cpu.space.CPUSpace(axes=("b", "w"), extents={"b": 1, "w": len(x_combined)}),
}
x_combined = np.asarray(x_combined).reshape((1, -1))
embeddings, embeddings_meta, embeddings_state = embedding_model.fprop(
x_combined, meta=dict(meta_combined), return_state=True
)
embeddings_meta["space_below"] = embeddings_meta["space_above"]
y_hat, y_hat_meta, log_reg_state = logistic_regression.fprop(
embeddings, meta=dict(embeddings_meta), return_state=True
)
y_hat_meta["space_below"] = y_hat_meta["space_above"]
loss, loss_meta, loss_state = objective.fprop(y_hat, max_error_label(y_hat), meta=dict(y_hat_meta))
delta, delta_meta = objective.bprop(y_hat, max_error_label(y_hat), meta=dict(loss_meta), fprop_state=loss_state)
delta = logistic_regression.bprop(delta, meta=dict(delta_meta), fprop_state=log_reg_state)
C = combiner_matrix(map(len, x))
sentence_delta = np.dot(delta, C)
sentence_embedding = np.dot(embeddings, C)
# normalize for cosine distance
sentence_delta /= np.sqrt(np.sum(sentence_delta ** 2, axis=1, keepdims=True))
sentence_embedding /= np.sqrt(np.sum(sentence_embedding ** 2, axis=1, keepdims=True))
sentence_importance_scores = np.abs(np.sum(sentence_delta * sentence_embedding, axis=0))
return sentence_importance_scores
def get_model_output(model, X,Y):
#Initializing the data provided
data_provider = cpu.optimize.data_provider.LabelledSequenceBatchProvider(
X=X, Y=Y, padding='PADDING')
#Define the cost function
cEntr = CrossEntropy()
#Get data and use the model to Predict
X, Y, meta = data_provider.next_batch()
Y_hat, meta, model_state = model.fprop(X, meta=meta, return_state=True)
#Create a Y that maximizes the error of the model
Y_inverted = enforce_error(Y_hat)
#Bookkeep the spaces and BPROP to get the deltas
meta['space_below'] = meta['space_above']
cost, meta, cost_state = cEntr.fprop(Y_hat, Y_inverted, meta=meta)
delta, meta = cEntr.bprop(Y_hat, Y_inverted, meta=meta, fprop_state=cost_state)
delta, meta = model.bprop(delta, meta=meta, fprop_state=model_state, return_state=True, num_layers=-1)
delta, space = meta['space_below'].transform(delta, ('b', 'w'))
return Y_hat, Y_inverted, delta
