def get_features(in_file, idf_enabled=False):
print "loading xml..."
lexical_tree = load_xml.get_pairs(in_file)
syntax_tree = create_tree.generate_syntax_tree(in_file)
print "done loading"
if idf_enabled:
generate_idf_score(lexical_tree)
print "parsing reference"
ref = get_attributes_pair(in_file)
print "extracting features"
features = defaultdict(list)
#word_matching
score = lexical.word_match(lexical_tree, idf_enabled=idf_enabled)
for k, v in score:
features[k].append(v)
#simple negation
score = lexical.get_simple_negations(lexical_tree)
for k, v in score:
features[k].append(v)
#tree edit distance
score = syntactic.tree_edit_distance(syntax_tree)
for k,v in score:
features[k].append(v)
#number_match
score = lexical.number_match(lexical_tree)
for k,v in score:
features[k].append(v)
#1,2,3-gram with synonyms of lemmas
for n in [1,2,3]:
score = bleu(lexical_tree, n=n, idf_enabled=True, lemma=True, synonyms=True)
for k,v in score:
features[k].append(v)
memory = {}
for n in [2]: # 2-gram without synonyms
score = bleu(lexical_tree, n=n, idf_enabled=True, lemma=True, synonyms=False)
for k,v in score:
features[k].append(v)
#appending task and entailment
for k,v in features.iteritems():
features[k].extend(ref[str(k)])
return features
def get_features(in_file, idf_enabled=False):
print "loading xml..."
lexical_tree = load_xml.get_pairs(in_file)
syntax_tree = create_tree.generate_syntax_tree(in_file)
print "done loading"
if idf_enabled:
generate_idf_score(lexical_tree)
print "parsing reference"
ref = get_attributes_pair(in_file)
print "extracting features"
features = defaultdict(list)
#word_matching
score = lexical.word_match(lexical_tree, idf_enabled=idf_enabled)
for k, v in score:
features[k].append(v)
#lemma_matching
score = lexical.lemma_match(lexical_tree)
for k, v in score:
features[k].append(v)
#bigram_matching (lemma)
score = lexical.bleu(lexical_tree, n=2, return_only_n=2,
idf_enabled=idf_enabled, lemma=True)
for k, v in score:
features[k].append(v)
#leamma_pos_matching
score = lexical.lemma_match(lexical_tree)
for k, v in score:
features[k].append(v)
#simple negation
score = lexical.get_simple_negations(lexical_tree)
for k, v in score:
features[k].append(v)
score = syntactic.tree_edit_distance(syntax_tree)
for k,v in score:
features[k].append(v)
#appending task and entailment
for k,v in features.iteritems():
features[k].extend(ref[str(k)])
return features
def main(tree, output, method, threshold, find_best, n=4, idf_enabled=False):
#load xml and idf
if method in ["word", "lemma", "bleu"]:
print "Loading xmlfile"
tree = (load_xml.get_pairs(tree), tree)
print "done."
if idf_enabled:
generate_idf_score(tree[0])
elif method in ["print_ted", "ted"]:
print "Loading xmlfile"
tree = (create_tree.generate_syntax_tree(tree), tree)
print "done."
if idf_enabled:
generate_idf_score(load_xml.get_pairs(tree[1]))
elif method in ["features"]:
features = get_features(tree, idf_enabled)
write_features(output, features)
return
elif method in ["knn", "knn-xv"]:
tree = (tree, tree)
#run methods
if find_best:
find_best_threshold(tree[0], METHODS[method], tree[1],
output, n=n, idf_enabled=idf_enabled)
else:
if method in ["knn", "knn-xv"]:
features = get_features(tree[0], idf_enabled=idf_enabled)
write_features("features.tab", features)
results = METHODS[method](None, outfile="features.tab")
else:
results = METHODS[method](tree[0], n=n, idf_enabled=idf_enabled,
output=output)
if method == "print_ted":
return
classification = classify_results(results, threshold)
print "writing output"
write(classification, output)
print "Accuracy = %.4f" % evaluate(tree[1], output)
