def create_representation(args):
rep_type = args['<representation>']
path = args['<representation_path>']
w_c = args['--w+c']
eig = float(args['--eig'])
if rep_type == 'PPMI':
if w_c:
raise Exception('w+c is not implemented for PPMI.')
else:
return Explicit.load(path, True)
elif rep_type == 'SVD':
if w_c:
return EnsembleEmbedding(SVDEmbedding(path, False, eig, False),
SVDEmbedding(path, False, eig, True),
True)
else:
return SVDEmbedding(path, True, eig)
else:
if w_c:
return EnsembleEmbedding(Embedding.load(path + '.words', False),
Embedding.load(path + '.contexts', False),
True)
else:
return Embedding.load(path, True)
def create_representation(rep_type, path, *args, **kwargs):
if rep_type == 'Explicit' or rep_type == 'PPMI':
return Explicit.load(path, *args, **kwargs)
elif rep_type == 'SVD':
return SVDEmbedding(path, *args, **kwargs)
elif rep_type == 'GIGA':
return GigaEmbedding(path, *args, **kwargs)
elif rep_type:
return Embedding.load(path, *args, **kwargs)
def create_representation(rep_type, path, *args, **kwargs):
if rep_type == 'Explicit' or rep_type == 'PPMI':
return Explicit.load(path, *args, **kwargs)
elif rep_type == 'SVD':
return SVDEmbedding(path, *args, **kwargs)
elif rep_type == 'GIGA':
return GigaEmbedding(path, *args, **kwargs)
elif rep_type == 'Embedding':
return Embedding.load(path, *args, **kwargs)
def _process_exp_sense(self, articles, which='test'):
exp_feat_name = FILE_PATH + '/../tmp/exp.feat'
expParser = Explicit()
exp_sense_file = codecs.open(exp_feat_name, 'w', 'utf-8')
for art in articles:
for rel in art.exp_relations:
expParser.print_features(rel, ['xxxxx'], which, exp_sense_file)
exp_sense_file.close()
exp_pred = FILE_PATH + '/../tmp/exp.pred'
Corpus.test_with_opennlp(exp_feat_name, expParser.model_file, exp_pred)
exp_res = [l.strip().split()[-1] for l in codecs.open(exp_pred, 'r', 'utf-8')]
rid = 0
for art in articles:
for rel in art.exp_relations:
pred_sense = exp_res[rid]
rel.sense = [pred_sense]
rid += 1
def _process_exp_sense(self, articles, which='test'):
exp_feat_name = FILE_PATH + '/../tmp/exp.feat'
expParser = Explicit()
exp_sense_file = codecs.open(exp_feat_name, 'w', 'utf-8')
for art in articles:
for rel in art.exp_relations:
expParser.print_features(rel, ['xxxxx'], which, exp_sense_file)
exp_sense_file.close()
exp_pred = FILE_PATH + '/../tmp/exp.pred'
Corpus.test_with_opennlp(exp_feat_name, expParser.model_file, exp_pred)
exp_res = [
l.strip().split()[-1] for l in codecs.open(exp_pred, 'r', 'utf-8')
]
rid = 0
for art in articles:
for rel in art.exp_relations:
pred_sense = exp_res[rid]
rel.sense = [pred_sense]
rid += 1
def _process_exp_sense(self, articles, which='test'):
exp_feat_name = FILE_PATH + '/../tmp/exp.feat'
expParser = Explicit()
exp_sense_file = open(exp_feat_name, 'w')
for art in articles:
for rel in art.exp_relations:
expParser.print_features(rel, ['Conjunction'], which, exp_sense_file)
exp_sense_file.close()
exp_vec = FILE_PATH + '/../tmp/exp.vec'
exp_pred = FILE_PATH + '/../tmp/exp.pred'
# Corpus.test_with_svm(exp_feat_name, expParser.feat_map_file, exp_vec, expParser.model_file, exp_pred)
Corpus.test_with_opennlp(exp_feat_name, expParser.model_file, exp_pred)
exp_res = [LABEL_SENSES_MAP[l.strip().split()[-1]] for l in open(exp_pred, 'r')]
rid = 0
for art in articles:
for rel in art.exp_relations:
pred_sense = exp_res[rid]
rel.sense = [pred_sense]
rid += 1
def simple_create_representation(rep_type,
path,
restricted_context=None,
thresh=None,
normalize=True):
if rep_type == 'PPMI':
return Explicit.load(path,
normalize=normalize,
restricted_context=restricted_context,
thresh=thresh)
else:
return Embedding.load(path, True)
def create_representation(args):
rep_type = args['<representation>']
path = args['<representation_path>']
w_c = args['--w+c']
eig = float(args['--eig'])
if rep_type == 'PPMI':
if w_c:
raise Exception('w+c is not implemented for PPMI.')
else:
return Explicit.load(path, True)
elif rep_type == 'SVD':
if w_c:
return EnsembleEmbedding(SVDEmbedding(path, False, eig, False), SVDEmbedding(path, False, eig, True), True)
else:
return SVDEmbedding(path, True, eig)
else:
if w_c:
return EnsembleEmbedding(Embedding.load(path + '.words', False), Embedding.load(path + '.contexts', False), True)
else:
return Embedding.load(path, True)
def simple_create_representation(rep_type, path, restricted_context=None, thresh=None, normalize=True):
if rep_type == 'PPMI':
return Explicit.load(path, normalize=normalize, restricted_context=restricted_context, thresh=thresh)
else:
return Embedding.load(path, True)