def get_pair_mentions_features(self, m1, m2):
''' Features for pair of mentions (same speakers, speaker mentioned, string match)'''
features_ = {"00_SameSpeaker": 1 if self.consider_speakers and m1.speaker == m2.speaker else 0,
"01_AntMatchMentionSpeaker": 1 if self.consider_speakers and m2.speaker_match_mention(m1) else 0,
"02_MentionMatchSpeaker": 1 if self.consider_speakers and m1.speaker_match_mention(m2) else 0,
"03_HeadsAgree": 1 if m1.heads_agree(m2) else 0,
"04_ExactStringMatch": 1 if m1.exact_match(m2) else 0,
"05_RelaxedStringMatch": 1 if m1.relaxed_match(m2) else 0,
"06_SentenceDistance": m2.utterances_sent - m1.utterances_sent,
"07_MentionDistance": m2.index - m1.index - 1,
"08_Overlapping": 1 if (m1.utterances_sent == m2.utterances_sent and m1.end > m2.start) else 0,
"09_M1Features": m1.features_,
"10_M2Features": m2.features_,
"11_DocGenre": self.genre_}
pairwise_features = [np.array([features_["00_SameSpeaker"],
features_["01_AntMatchMentionSpeaker"],
features_["02_MentionMatchSpeaker"],
features_["03_HeadsAgree"],
features_["04_ExactStringMatch"],
features_["05_RelaxedStringMatch"]]),
encode_distance(features_["06_SentenceDistance"]),
encode_distance(features_["07_MentionDistance"]),
np.array(features_["08_Overlapping"], ndmin=1),
m1.features,
m2.features,
self.genre]
return (features_, np.concatenate(pairwise_features, axis=0))
def set_mentions_features(self):
'''
Compute features for the extracted mentions
'''
doc_embedding = self.embed_extractor.get_document_embedding(self.utterances) if self.embed_extractor is not None else None
for mention in self.mentions:
one_hot_type = np.zeros((4,))
one_hot_type[mention.mention_type] = 1
features_ = {"01_MentionType": mention.mention_type,
"02_MentionLength": len(mention)-1,
"03_MentionNormLocation": (mention.index)/len(self.mentions),
"04_IsMentionNested": 1 if any((m is not mention
and m.utterances_sent == mention.utterances_sent
and m.start <= mention.start
and mention.end <= m.end)
for m in self.mentions) else 0}
features = np.concatenate([one_hot_type,
encode_distance(features_["02_MentionLength"]),
np.array(features_["03_MentionNormLocation"], ndmin=1, copy=False),
np.array(features_["04_IsMentionNested"], ndmin=1, copy=False)
], axis=0)
(spans_embeddings_, words_embeddings_,
spans_embeddings, words_embeddings) = self.embed_extractor.get_mention_embeddings(mention, doc_embedding)
mention.features_ = features_
mention.features = features
mention.spans_embeddings = spans_embeddings
mention.spans_embeddings_ = spans_embeddings_
mention.words_embeddings = words_embeddings
mention.words_embeddings_ = words_embeddings_
def __getitem__(self, mention_idx, debug=False):
"""
Return:
Definitions:
P is the number of antecedent per mention (number of pairs for the mention)
S = 250 is the size of the span vector (averaged word embeddings)
W = 8 is the number of words in a mention (tuned embeddings)
Fp = 70 is the number of features for a pair of mention
Fs = 24 is the number of features of a single mention
if there are some pairs:
inputs = (spans, words, features, ant_spans, ant_words, ana_spans, ana_words, pairs_features)
targets = (labels, costs, true_ants, false_ants)
else:
inputs = (spans, words, features)
targets = (labels, costs, true_ants)
inputs: Tuple of
spans => (S,)
words => (W,)
features => (Fs,)
+ if there are potential antecedents (P > 0):
ant_spans => (P, S) or nothing if no pairs
ant_words => (P, W) or nothing if no pairs
ana_spans => (P, S) or nothing if no pairs
ana_words => (P, W) or nothing if no pairs
pair_features => (P, Fp) or nothing if no pairs
targets: Tuple of
labels => (P+1,)
costs => (P+1,)
true_ant => (P+1,)
+ if there are potential antecedents (P > 0):
false_ant => (P+1,)
"""
features_raw, label, pairs_length, pairs_start_index, spans, words = self.mentions[mention_idx]
pairs_start_index = np.asscalar(pairs_start_index)
pairs_length = np.asscalar(pairs_length)
# Build features array (float) from raw features (int)
assert features_raw.shape[0] == SIZE_FS_COMPRESSED
features = np.zeros((SIZE_FS,))
features[features_raw[0]] = 1
features[4:15] = encode_distance(features_raw[1])
features[15] = features_raw[2].astype(float) / features_raw[3].astype(float)
features[16] = features_raw[4]
features[features_raw[5] + 17] = 1
if pairs_length == 0:
spans = torch.from_numpy(spans).float()
words = torch.from_numpy(words)
features = torch.from_numpy(features).float()
inputs = (spans, words, features)
if self.no_targets:
return inputs
true_ant = torch.zeros(1).long() # zeros = indices of true ant
costs = torch.from_numpy((1 - label) * self.costs['FN']).float()
label = torch.from_numpy(label).float()
targets = (label, costs, true_ant)
if debug:
print("inputs shapes: ", [a.size() for a in inputs])
print("targets shapes: ", [a.size() for a in targets])
return inputs, targets
start = pairs_start_index
end = pairs_start_index + pairs_length
pairs = self.pairs[start:end]
assert len(pairs) == pairs_length
assert len(pairs[0]) == 3 # pair[i] = (pairs_ant_index, pairs_features, pairs_labels)
pairs_ant_index, pairs_features_raw, pairs_labels = list(zip(*pairs))
pairs_features_raw = np.stack(pairs_features_raw)
pairs_labels = np.squeeze(np.stack(pairs_labels), axis=1)
# Build pair features array (float) from raw features (int)
assert pairs_features_raw[0, :].shape[0] == SIZE_FP_COMPRESSED
pairs_features = np.zeros((len(pairs_ant_index), SIZE_FP))
pairs_features[:, 0:6] = pairs_features_raw[:, 0:6]
pairs_features[:, 6:17] = encode_distance(pairs_features_raw[:, 6])
pairs_features[:, 17:28] = encode_distance(pairs_features_raw[:, 7])
pairs_features[:, 28] = pairs_features_raw[:, 8]
# prepare antecent features
ant_features_raw = np.concatenate([self.mentions[np.asscalar(idx)][0][np.newaxis, :] for idx in pairs_ant_index])
ant_features = np.zeros((pairs_length, SIZE_FS-SIZE_GENRE))
ant_features[:, ant_features_raw[:, 0]] = 1
ant_features[:, 4:15] = encode_distance(ant_features_raw[:, 1])
ant_features[:, 15] = ant_features_raw[:, 2].astype(float) / ant_features_raw[:, 3].astype(float)
ant_features[:, 16] = ant_features_raw[:, 4]
pairs_features[:, 29:46] = ant_features
# Here we keep the genre
ana_features = np.tile(features, (pairs_length, 1))
pairs_features[:, 46:] = ana_features
ant_spans = np.concatenate([self.mentions[np.asscalar(idx)][4][np.newaxis, :] for idx in pairs_ant_index])
ant_words = np.concatenate([self.mentions[np.asscalar(idx)][5][np.newaxis, :] for idx in pairs_ant_index])
ana_spans = np.tile(spans, (pairs_length, 1))
ana_words = np.tile(words, (pairs_length, 1))
ant_spans = torch.from_numpy(ant_spans).float()
ant_words = torch.from_numpy(ant_words)
ana_spans = torch.from_numpy(ana_spans).float()
ana_words = torch.from_numpy(ana_words)
pairs_features = torch.from_numpy(pairs_features).float()
labels_stack = np.concatenate((pairs_labels, label), axis=0)
assert labels_stack.shape == (pairs_length + 1,)
labels = torch.from_numpy(labels_stack).float()
spans = torch.from_numpy(spans).float()
words = torch.from_numpy(words)
features = torch.from_numpy(features).float()
inputs = (spans, words, features,
ant_spans, ant_words,
ana_spans, ana_words,
pairs_features)
if self.no_targets:
return inputs
if label == 0:
costs = np.concatenate((self.costs['WL'] * (1 - pairs_labels), [self.costs['FN']])) # Inverse labels: 1=>0, 0=>1
else:
costs = np.concatenate((self.costs['FL'] * np.ones_like(pairs_labels), [0]))
assert costs.shape == (pairs_length + 1,)
costs = torch.from_numpy(costs).float()
true_ants_unpad = np.flatnonzero(labels_stack)
if len(true_ants_unpad) == 0:
raise ValueError("Error: no True antecedent for mention")
true_ants = np.pad(true_ants_unpad, (0, len(pairs_labels) + 1 - len(true_ants_unpad)), 'edge')
assert true_ants.shape == (pairs_length + 1,)
true_ants = torch.from_numpy(true_ants).long()
false_ants_unpad = np.flatnonzero(1 - labels_stack)
assert len(false_ants_unpad) != 0
false_ants = np.pad(false_ants_unpad, (0, len(pairs_labels) + 1 - len(false_ants_unpad)), 'edge')
assert false_ants.shape == (pairs_length + 1,)
false_ants = torch.from_numpy(false_ants).long()
targets = (labels, costs, true_ants, false_ants)
if debug:
print("Mention", mention_idx)
print("inputs shapes: ", [a.size() for a in inputs])
print("targets shapes: ", [a.size() for a in targets])
return inputs, targets