def _losses_single(self,
score_expr,
gold_idxes_expr,
single_sample,
is_hinge=False,
margin=0.):
# expand the idxes to 0/1
score_shape = BK.get_shape(score_expr)
expanded_idxes_expr = BK.constants(score_shape, 0.)
expanded_idxes_expr = BK.minus_margin(expanded_idxes_expr,
gold_idxes_expr,
-1.) # minus -1 means +1
# todo(+N): first adjust margin, since previously only minus margin for golds?
if margin > 0.:
adjusted_scores = margin + BK.minus_margin(score_expr,
gold_idxes_expr, margin)
else:
adjusted_scores = score_expr
# [*, L]
if is_hinge:
# multiply pos instances with -1
flipped_scores = adjusted_scores * (1. - 2 * expanded_idxes_expr)
losses_all = BK.clamp(flipped_scores, min=0.)
else:
losses_all = BK.binary_cross_entropy_with_logits(
adjusted_scores, expanded_idxes_expr, reduction='none')
# special interpretation (todo(+2): there can be better implementation)
if single_sample < 1.:
# todo(warn): lower bound of sample_rate, ensure 2 samples
real_sample_rate = max(single_sample, 2. / score_shape[-1])
elif single_sample >= 2.:
# including the positive one
real_sample_rate = max(single_sample, 2.) / score_shape[-1]
else: # [1., 2.)
real_sample_rate = single_sample
#
if real_sample_rate < 1.:
sample_weight = BK.random_bernoulli(score_shape, real_sample_rate,
1.)
# make sure positive is valid
sample_weight = (sample_weight +
expanded_idxes_expr.float()).clamp_(0., 1.)
#
final_losses = (losses_all *
sample_weight).sum(-1) / sample_weight.sum(-1)
else:
final_losses = losses_all.mean(-1)
return final_losses
def _losses_global_prob(self, full_score_expr, gold_heads_expr,
gold_labels_expr, marginals_expr, mask_expr):
# combine the last two dimension
full_shape = BK.get_shape(full_score_expr)
last_size = full_shape[-1]
# [*, m, h*L]
combined_marginals_expr = marginals_expr.view(full_shape[:-2] + [-1])
# # todo(warn): make sure sum to 1., handled in algorithm instead
# combined_marginals_expr = combined_marginals_expr / combined_marginals_expr.sum(dim=-1, keepdim=True)
# [*, m]
gold_combined_idx_expr = gold_heads_expr * last_size + gold_labels_expr
# [*, m, h, L]
gradients = BK.minus_margin(combined_marginals_expr,
gold_combined_idx_expr,
1.).view(full_shape)
# the gradients on h are already 0. from the marginal algorithm
gradients_masked = gradients * mask_expr.unsqueeze(-1).unsqueeze(
-1) * mask_expr.unsqueeze(-2).unsqueeze(-1)
# for the h-dimension, need to divide by the real length.
# todo(warn): this values should be directly summed rather than averaged, since directly from loss
fake_losses = (full_score_expr * gradients_masked).sum(-1).sum(
-1) # [BS, m]
# todo(warn): be aware of search-error-like output constrains;
# but this clamp for all is not good for loss-prob, dealt at outside with unproj-mask.
# <bad> fake_losses = BK.clamp(fake_losses, min=0.)
return fake_losses
def _score_label_full(self,
scoring_expr_pack,
mask_expr,
training,
margin,
gold_heads_expr=None,
gold_labels_expr=None):
_, _, lm_expr, lh_expr = scoring_expr_pack
# [BS, len-m, len-h, L]
full_label_score = self.scorer.score_label_all(lm_expr, lh_expr,
mask_expr, mask_expr)
# # set diag to small values # todo(warn): handled specifically in algorithms
# maxlen = BK.get_shape(full_label_score, 1)
# full_label_score += BK.diagflat(BK.constants([maxlen], Constants.REAL_PRAC_MIN)).unsqueeze(-1)
# margin? -- specially reshaping
if training and margin > 0.:
full_shape = BK.get_shape(full_label_score)
# combine last two dim
combiend_score_expr = full_label_score.view(full_shape[:-2] + [-1])
combined_idx_expr = gold_heads_expr * full_shape[
-1] + gold_labels_expr
combined_changed_score = BK.minus_margin(combiend_score_expr,
combined_idx_expr, margin)
full_label_score = combined_changed_score.view(full_shape)
return full_label_score
def _score_arc_full(self,
scoring_expr_pack,
mask_expr,
training,
margin,
gold_heads_expr=None):
am_expr, ah_expr, _, _ = scoring_expr_pack
# [BS, len-m, len-h]
full_arc_score = self.scorer.score_arc_all(am_expr, ah_expr, mask_expr,
mask_expr)
# # set diag to small values # todo(warn): handled specifically in algorithms
# maxlen = BK.get_shape(full_arc_score, 1)
# full_arc_score += BK.diagflat(BK.constants([maxlen], Constants.REAL_PRAC_MIN))
# margin?
if training and margin > 0.:
full_arc_score = BK.minus_margin(full_arc_score, gold_heads_expr,
margin)
return full_arc_score
def _score_label_selected(self,
scoring_expr_pack,
mask_expr,
training,
margin,
gold_heads_expr,
gold_labels_expr=None):
_, _, lm_expr, lh_expr = scoring_expr_pack
# [BS, len-m, D]
lh_expr_shape = BK.get_shape(lh_expr)
selected_lh_expr = BK.gather(
lh_expr,
gold_heads_expr.unsqueeze(-1).expand(*lh_expr_shape),
dim=len(lh_expr_shape) - 2)
# [BS, len-m, L]
select_label_score = self.scorer.score_label_select(
lm_expr, selected_lh_expr, mask_expr)
# margin?
if training and margin > 0.:
select_label_score = BK.minus_margin(select_label_score,
gold_labels_expr, margin)
return select_label_score
