def get_features(ptree: nltk.ParentedTree, dtree: List[DepRel], indices, sense, offset):
features_sentence = []
for i, drel in enumerate(dtree):
if drel.rel.lower() == 'root':
mv_position = i
break
else:
mv_position = 0
main_verb = lemmatizer.lemmatize(ptree.pos()[mv_position][0])
for i, (word, tag) in enumerate(ptree.pos()):
tree_pos = ptree.treeposition_spanning_leaves(i, i + 1)[:-2]
chain = [ptree[tree_pos[:i + 1]].label() for i in range(len(tree_pos))]
chain = ['S' if c == 'SBAR' else c for c in chain]
if len(chain) > 0:
chain = "-".join(get_compressed_chain(chain))
stem = stemmer.stem(word).lower()
features_word = {
'idx': offset + i,
'BOS': i == 0,
'word': word.lower(),
'pos': tag,
'lemma': lemmatizer.lemmatize(word).lower(),
'stem': stem.lower(),
'chain': chain,
'conn': sense.split('.')[0] if offset + i in indices else "",
'inflection': word[len(stem):],
'is_main_verb': i == mv_position,
'main_verb': main_verb.lower()
}
features_sentence.append(features_word)
return features_sentence
def get_features(ptree: nltk.ParentedTree, conn_idxs: List[int]):
features = []
for i, (word, tag) in enumerate(ptree.pos()):
features.append({
'BOS': i == 0,
'word': word,
'pos': tag,
'lemma': lemmatizer.lemmatize(word),
'stem': stemmer.stem(word),
'conn': i in conn_idxs
})
return features
