i += 1
nps = reconcile.getNPs(f)
gold_chains = reconcile.getGoldChains(f)
try:
all_pairs = reconcile.getFauxPairs(f, PREDICTIONS)
except:
continue
response_pairs = []
for pair in all_pairs:
if pair[0] is None or pair[1] is None:
continue
response_pairs.append(pair)
labeled_annots = reconcile.labelCorrectPairs(gold_chains,
response_pairs)
for pair in labeled_annots:
if ACE:
if pair[2]:
processACE(f, pair[1], correct_qps)
else:
processACE(f, pair[1], incorrect_qps)
sys.stderr.write("\r \r\n")
print(len(list(correct_qps.keys())))
print(len(list(incorrect_qps.keys())))
columns = {}
with open("/home/ngilbert/public_html/ace.qp.html", 'w') as htmlFile:
htmlFile.write("<html>\n")
htmlFile.write("\t<head><title>ACE QP Results</title></head>\n")
continue
#get the sentences
sentences = reconcile.getSentences(f)
#remove the pairs we don't care about
tracked_pairs = []
for pair in faux_pronoun_pairs:
ana_head = specificity_utils.getHead(pair[1].getText()).lower()
if ana_head in FAUX_PRONOUNS:
if ana_head not in list(tracked_nouns.keys()):
tracked_nouns[ana_head] = Noun(ana_head)
tracked_pairs.append(pair)
#label the correct or incorrect pairs
labeled_faux_pairs = reconcile.labelCorrectPairs(gold_chains,
tracked_pairs)
for lpair in labeled_faux_pairs:
ana_head = specificity_utils.getHead(lpair[1].getText()).lower()
key = "{0}:{1}:{2}".format(f, lpair[1].getStart(),
lpair[1].getEnd())
tracked_nouns[ana_head].instances[key] = utils.textClean(lpair[1].getText())
tracked_nouns[ana_head].antecedents[key] = utils.textClean(lpair[0].getText())
tracked_nouns[ana_head].labels[key] = lpair[2]
#this is an incorrect antecedent
if not lpair[2]:
closest_true_antecedent = closest_antecedent(gold_chains,
lpair[1])
# pairs.append(pair)
elif "-baseline" in sys.argv:
RESPONSE_TYPE = "Baseline"
baseline_pairs = reconcile.getFauxPairs(
f, "features.goldnps/predictions.Baseline.byte_dist")
for pair in baseline_pairs:
tags = pos.getSubset(pair[1].getStart(), pair[1].getEnd())
text = utils.textClean(pair[1].getText()).lower()
ana_head = qp_utils.getHead2(text, tags)
if ana_head in QPs:
pairs.append(pair)
else:
print("Please select response type.")
sys.exit(1)
labeled_annots = reconcile.labelCorrectPairs(gold_chains, pairs)
for pair in labeled_annots:
total_scores["vps_guessed"] += 1
if pair[2]:
print(pair[0].ppprint() + " <- " + pair[1].ppprint())
total_scores["vps_correct"] += 1
else:
print(pair[0].ppprint() + " <- " + pair[1].ppprint() + "*")
print("=" * 72)
print("{0} accuracy".format(RESPONSE_TYPE))
try:
result = total_scores["vps_correct"] / float(
total_scores["vps_guessed"])
print("Total: {0} / {1} = {2:0.2f}".format(total_scores["vps_correct"],
total_scores["vps_guessed"],
files.extend([
x for x in [x.strip() for x in fileList.readlines()]
if not x.startswith("#")
])
total_new_correct_resolutions = 0
total_new_incorrect_resolutions = 0
for f in files:
print("File: {0}".format(f))
response1 = reconcile.getAllResponsePairs(
f, "/features." + base + "/" + predictions1)
response2 = reconcile.getAllResponsePairs(
f, "/features." + second + "/" + predictions2)
gold_chains = reconcile.getGoldChains(f)
gold_response1 = reconcile.labelCorrectPairs(gold_chains, response1)
gold_system1_pairs = {}
for pair in gold_response1:
key = "%s:%s" % (pair[0].getID(), pair[1].getID())
gold_system1_pairs[key] = pair
gold_system2_pairs = {}
gold_response2 = reconcile.labelCorrectPairs(gold_chains, response2)
for pair in gold_response2:
key = "%s:%s" % (pair[0].getID(), pair[1].getID())
gold_system2_pairs[key] = pair
system1_pairs = {}
system2_pairs = {}
for pair in response1:
if pair[2] > 0: