def syntax_matching(pair_attributes, distances, threshold):
""" Calculates entailment values based on the tree edit distances and threshold """
n = len(pair_attributes)
entailments = [0 for foo in range(n+1)]
results = [0 for foo in range(n+1)]
# Calculates entailments and accuracy
for i in range(n):
t,h,id_num,e,ta = pair_attributes[i]
id_num = int(id_num)
entails = distances[i] < threshold
entailments[id_num] = "YES" if entails else "NO"
results[id_num] = 1 if entailments[id_num] == e else 0
lexical.output_rte(entailments)
print "Threshold: " + "%.3f"%threshold + " Accuracy: " + str(float(sum(results)) / float(n))
def bleu_matching(threshold, pairs):
pair_attributes = pairs[:]
n = len(pair_attributes)
results = [0 for foo in range(n+1)]
entailments = [0 for foo in range(n+1)]
for i in range(n):
t,h,id_num,e,ta = pair_attributes[i]
id_num = int(id_num)
t_lemmas,pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas,pos = xml_util.get_lemmas_from_text_node(h)
entailments[id_num] = calculate_entailment(t_lemmas,h_lemmas,threshold)
if e == entailments[id_num]:
results[id_num] = 1
lexical.output_rte(entailments)
print "Threshold: " + "%.2f"%threshold + " Accuracy: " + str(float(sum(results)) / float(n))
def bleu_matching(threshold, pairs):
pair_attributes = pairs[:]
n = len(pair_attributes)
results = [0 for foo in range(n + 1)]
entailments = [0 for foo in range(n + 1)]
for i in range(n):
t, h, id_num, e, ta = pair_attributes[i]
id_num = int(id_num)
t_lemmas, pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas, pos = xml_util.get_lemmas_from_text_node(h)
entailments[id_num] = calculate_entailment(t_lemmas, h_lemmas,
threshold)
if e == entailments[id_num]:
results[id_num] = 1
lexical.output_rte(entailments)
print "Threshold: " + "%.2f" % threshold + " Accuracy: " + str(
float(sum(results)) / float(n))
def idf_weighting(threshold, pairs):
pair_attributes = pairs[:]
words = []
documents = []
n = len(pair_attributes)
results = [0 for foo in range(n + 1)]
entailments = [0 for foo in range(n + 1)]
# Starts by adding all the words to the list 'words' and then making a set of these words
# Also makes a list of documents where each document is a set of all the words in a given
# (text, hypothesis) pair.
for i in range(n):
t, h, id_num, e, ta = pair_attributes[i]
t_lemmas, pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas, pos = xml_util.get_lemmas_from_text_node(h)
doc = []
for word in t_lemmas:
words.append(word.lower())
doc.append(word.lower())
for word in h_lemmas:
words.append(word.lower())
doc.append(word.lower())
documents.append(set(doc))
word_set = set(words)
# Creates a dictionary 'idf_dict' that can be used to count how many document each word is present in
idf_dict = {}
# Starts by initiating the count for all words to 0
for word in word_set:
idf_dict[word] = 0
# Then calculates the number of documents each word in the word_set appears in
for word in word_set:
for document in documents:
if word in document:
idf_dict[word] += 1
print "dict done"
for i in range(n):
t, h, id_num, e, ta = pair_attributes[i]
id_num = int(id_num)
t_lemmas, pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas, pos = xml_util.get_lemmas_from_text_node(h)
entailments[id_num] = calculate_entailment(t_lemmas, h_lemmas,
idf_dict, threshold)
results[id_num] = 1 if e == entailments[id_num] else 0
lexical.output_rte(entailments)
print "Threshold: " + "%.2f" % threshold + " Accuracy: " + str(
float(sum(results)) / float(n))
def idf_weighting(threshold, pairs):
pair_attributes = pairs[:]
words = []
documents = []
n = len(pair_attributes)
results = [0 for foo in range(n + 1)]
entailments = [0 for foo in range(n + 1)]
# Starts by adding all the words to the list 'words' and then making a set of these words
# Also makes a list of documents where each document is a set of all the words in a given
# (text, hypothesis) pair.
for i in range(n):
t, h, id_num, e, ta = pair_attributes[i]
t_lemmas, pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas, pos = xml_util.get_lemmas_from_text_node(h)
doc = []
for word in t_lemmas:
words.append(word.lower())
doc.append(word.lower())
for word in h_lemmas:
words.append(word.lower())
doc.append(word.lower())
documents.append(set(doc))
word_set = set(words)
# Creates a dictionary 'idf_dict' that can be used to count how many document each word is present in
idf_dict = {}
# Starts by initiating the count for all words to 0
for word in word_set:
idf_dict[word] = 0
# Then calculates the number of documents each word in the word_set appears in
for word in word_set:
for document in documents:
if word in document:
idf_dict[word] += 1
print "dict done"
for i in range(n):
t, h, id_num, e, ta = pair_attributes[i]
id_num = int(id_num)
t_lemmas, pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas, pos = xml_util.get_lemmas_from_text_node(h)
entailments[id_num] = calculate_entailment(t_lemmas, h_lemmas, idf_dict, threshold)
results[id_num] = 1 if e == entailments[id_num] else 0
lexical.output_rte(entailments)
print "Threshold: " + "%.2f" % threshold + " Accuracy: " + str(float(sum(results)) / float(n))
def lemma_matching(threshold, pairs):
pair_attributes = pairs[:]
n = len(pair_attributes)
results = [0 for foo in range(n+1)]
entailments = [0 for foo in range(n+1)]
for i in range(n):
t,h,id_num,e,ta = pair_attributes[i]
id_num = int(id_num)
t_lemmas,t_pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas,h_pos = xml_util.get_lemmas_from_text_node(h)
text = []
for i in range(len(t_lemmas)):
text.append((t_lemmas[i],t_pos[i]))
hypothesis = []
for i in range(len(h_lemmas)):
hypothesis.append((h_lemmas[i],h_pos[i]))
entailments[id_num] = calculate_entailment(text,hypothesis,threshold)
if (e == entailments[id_num]):
results[id_num] = 1
else:
results[id_num] = 0
lexical.output_rte(entailments)
print "Threshold: " + "%.2f"%threshold + " Accuracy: " + str(float(sum(results)) / float(n))
def lemma_matching(threshold, pairs):
pair_attributes = pairs[:]
n = len(pair_attributes)
results = [0 for foo in range(n + 1)]
entailments = [0 for foo in range(n + 1)]
for i in range(n):
t, h, id_num, e, ta = pair_attributes[i]
id_num = int(id_num)
t_lemmas, t_pos = xml_util.get_lemmas_from_text_node(t)
h_lemmas, h_pos = xml_util.get_lemmas_from_text_node(h)
text = []
for i in range(len(t_lemmas)):
text.append((t_lemmas[i], t_pos[i]))
hypothesis = []
for i in range(len(h_lemmas)):
hypothesis.append((h_lemmas[i], h_pos[i]))
entailments[id_num] = calculate_entailment(text, hypothesis, threshold)
if (e == entailments[id_num]):
results[id_num] = 1
else:
results[id_num] = 0
lexical.output_rte(entailments)
print "Threshold: " + "%.2f" % threshold + " Accuracy: " + str(
float(sum(results)) / float(n))