def separate_dataset(self, in_file, out_file, check_function):
"""
This function is used to separate the original word similarity dataset.
word similarity of noun: noun_rg.txt, noun_mc.txt, noun_ws353.txt, noun_ws353-sim.txt, noun_simlex.txt
the lcs is in knowledge graph: graph_rg.txt, graph_mc.txt, graph_ws353.txt,
graph_ws353-sim.txt, graph_simlex.txt
both words are in knowledge graph: type_rg.txt, type_mc.txt, type_ws353.txt, type_ws353-sim.txt,
type_simlex.txt
:param in_file: source dataset file
:param out_file: target dataset file
:param check_function: the function of mapping criteria for deciding the word pairs.
:return:
"""
out_data = []
word_pairs, human = self.load_dataset(in_file)
for i, pairs in enumerate(word_pairs):
w1, w2 = pairs
h = human[i]
if check_function(w1, w2):
out_data.append(' '.join([w1, w2, str(h)]))
FileIO.save_list_file('dataset/wordsim/%s.txt' % out_file, out_data)
def separate_dataset(self, in_file, out_file, check_function):
"""
This function is used to separate the original word similarity dataset.
word similarity of noun: noun_rg.txt, noun_mc.txt, noun_ws353.txt, noun_ws353-sim.txt, noun_simlex.txt
the lcs is in knowledge graph: graph_rg.txt, graph_mc.txt, graph_ws353.txt,
graph_ws353-sim.txt, graph_simlex.txt
both words are in knowledge graph: type_rg.txt, type_mc.txt, type_ws353.txt, type_ws353-sim.txt,
type_simlex.txt
:param in_file: source dataset file
:param out_file: target dataset file
:param check_function: the function of mapping criteria for deciding the word pairs.
:return:
"""
out_data = []
word_pairs, human = self.load_dataset(in_file)
for i, pairs in enumerate(word_pairs):
w1, w2 = pairs
h = human[i]
if check_function(w1, w2):
out_data.append(' '.join([w1, w2, str(h)]))
FileIO.save_list_file('eval/word_similarity/%s.txt' % out_file, out_data)
def save_result(self, cor, sim_values, sim_name, dataset_name):
"""
This function save the result computed by a similarity metric
:param cor: correlation with human rating
:param sim_values: similarity scores for word pairs
:param sim_name: the name of similarity metric
:param dataset_name: the name of word similarity dataset
:return:
"""
data = ["%.3f" % cor]
data += map(lambda x: "%.3f" % x, sim_values)
FileIO.save_list_file('dataset/wordsim/results/%s-%s.txt' % (dataset_name, sim_name), data)
def save_result(self, cor, sim_values, sim_name, dataset_name):
"""
This function save the result computed by a similarity metric
:param cor: correlation with human rating
:param sim_values: similarity scores for word pairs
:param sim_name: the name of similarity metric
:param dataset_name: the name of word similarity dataset
:return:
"""
data = ["%.3f" % cor]
data += map(lambda x: "%.3f" % x, sim_values)
FileIO.save_list_file('eval/word_similarity/results/%s-%s.txt' % (dataset_name, sim_name), data)
def evaluate(self, input_file, output_file):
"""
Evaluate the sentence similarity
:param input_file: corpus file
:param output_file: result file
:return: similarity scores of text pairs
"""
corpus = self.load_dataset(input_file)
print 'dataset size: ', len(corpus)
result = [self._sim_metric(t1, t2) for t1, t2 in corpus]
result = map(lambda x:"%.3f" % round(x,3), result)
FileIO.save_list_file(output_file, result)
return result
def evaluate(self, input_file, output_file):
"""
Evaluate the sentence similarity
:param input_file: corpus file
:param output_file: result file
:return: similarity scores of text pairs
"""
corpus = self.load_dataset(input_file)
print 'dataset size: ', len(corpus)
result = [self._sim_metric(t1, t2) for t1, t2 in corpus]
result = map(lambda x: "%.3f" % round(x, 3), result)
FileIO.save_list_file(output_file, result)
return result