def parse(text):
log("Checking for coherence in '{0}'".format(text), 2)
family_hits = []
family_stem_words = stemmed_words(family_words, 'family_words')
for sentence in sentence_tokenizer.parse(text):
tree = parsers.parse(sentence)[0]
family_hits += [
(a_tree.node, a_tree[0].lower(), stemmer.stem(a_tree[0].lower())
in family_stem_words)
for a_tree in tree.subtrees(lambda x: x.node in noun_tags)
]
log("Family hits: {0}".format(family_hits), 4)
family_hit_values = (len([hit for hit in family_hits
if hit[2]]), len(family_hits))
log("%d/%d" % family_hit_values, 3)
work_hits = []
work_stem_words = stemmed_words(work_words, 'work_words')
for sentence in sentence_tokenizer.parse(text):
tree = parsers.parse(sentence)[0]
work_hits += [
(a_tree.node, a_tree[0].lower(), stemmer.stem(a_tree[0].lower())
in work_stem_words)
for a_tree in tree.subtrees(lambda x: x.node in noun_tags)
]
log("Work hits: {0}".format(work_hits), 4)
work_hit_values = (len([hit for hit in work_hits
if hit[2]]), len(work_hits))
log("%d/%d" % work_hit_values, 3)
return family_hit_values[0], work_hit_values[0], work_hit_values[1]
def grade_3a(text):
sentences = sentence_tokenizer.parse(text)
num_sentences = len(sentences)
if num_sentences >= 6:
return 5
else:
return max(num_sentences - 1, 1)
def grade_3a(text):
sentences = sentence_tokenizer.parse(text)
num_sentences = len(sentences)
if num_sentences >= 6:
return 5
else:
return max(num_sentences - 1, 1)
def parse(text):
log("Checking for coherence in '{0}'".format(text), 2)
family_hits = []
family_stem_words = stemmed_words(family_words, 'family_words')
for sentence in sentence_tokenizer.parse(text):
tree = parsers.parse(sentence)[0]
family_hits += [(a_tree.node, a_tree[0].lower(), stemmer.stem(a_tree[0].lower()) in family_stem_words) for a_tree in tree.subtrees(lambda x: x.node in noun_tags)]
log("Family hits: {0}".format(family_hits), 4)
family_hit_values = (len([hit for hit in family_hits if hit[2]]), len(family_hits))
log("%d/%d" % family_hit_values, 3)
work_hits = []
work_stem_words = stemmed_words(work_words, 'work_words')
for sentence in sentence_tokenizer.parse(text):
tree = parsers.parse(sentence)[0]
work_hits += [(a_tree.node, a_tree[0].lower(), stemmer.stem(a_tree[0].lower()) in work_stem_words) for a_tree in tree.subtrees(lambda x: x.node in noun_tags)]
log("Work hits: {0}".format(work_hits), 4)
work_hit_values = (len([hit for hit in work_hits if hit[2]]), len(work_hits))
log("%d/%d" % work_hit_values, 3)
return family_hit_values[0], work_hit_values[0], work_hit_values[1]
def grade_1a(text):
sentences = sentence_tokenizer.parse(text)
num_problems = 0
num_sentences = 0
for sentence in sentences:
issues_in_sentence = word_order.issues_in_sentence(sentence)
num_sentences += 1
num_problems += len(issues_in_sentence)
if num_problems in (0, 1):
return 5
elif num_problems == 2:
return 4
elif num_problems in (3, 4):
return 3
elif num_problems in (5, 6):
return 2
else:
return 1
def grade_1a(text):
sentences = sentence_tokenizer.parse(text)
num_problems = 0
num_sentences = 0
for sentence in sentences:
issues_in_sentence = word_order.issues_in_sentence(sentence)
num_sentences += 1
num_problems += len(issues_in_sentence)
if num_problems in (0, 1):
return 5
elif num_problems == 2:
return 4
elif num_problems in (3, 4):
return 3
elif num_problems in (5, 6):
return 2
else:
return 1
def parse(text):
treebank_rules = get_treebank_rules(cutoff=0)
sentence_probs = []
for line in text.split("\n"):
sentences = sentence_tokenizer.parse(line)
for sentence in sentences:
# Add a period to the end of the sentence, which sometimes
# forces a better parse
#if sentence[-1] not in ('.', '!', '?'):
# sentence += '.'
parse_trees = parsers.parse(sentence)
for tree in parse_trees:
if cmd_utils.cmd_log_level() > 2:
print tree.pprint()
evindenced_lexical_rules = set(lexical_rules(tree).keys())
differences = evindenced_lexical_rules.difference(
treebank_rules)
bad_generations = len(differences)
log(
"Found {0} bad generations ({1})".format(
bad_generations, differences), 3)
#bad_parse_prob = 1 if prob == 0 else 0
#log("Scored {0} for prob {1}".format(bad_parse_prob, prob), 3)
bad_tag_problems = num_tag_problems(tree)
log("Found {0} X or FRAG tags".format(bad_tag_problems), 3)
bad_sbar_problems = num_sbar_problems(tree)
log("Found {0} bad SBAR issues".format(bad_sbar_problems), 3)
total_problems = bad_sbar_problems + bad_tag_problems + bad_generations
log("In '{0}'".format(sentence), 2)
log(
"Found {0} sentence formation problems".format(
total_problems), 1)
sentence_probs.append(total_problems)
return sentence_probs
def parse(text):
treebank_rules = get_treebank_rules(cutoff=0)
sentence_probs = []
for line in text.split("\n"):
sentences = sentence_tokenizer.parse(line)
for sentence in sentences:
# Add a period to the end of the sentence, which sometimes
# forces a better parse
#if sentence[-1] not in ('.', '!', '?'):
# sentence += '.'
parse_trees = parsers.parse(sentence)
for tree in parse_trees:
if cmd_utils.cmd_log_level() > 2:
print tree.pprint()
evindenced_lexical_rules = set(lexical_rules(tree).keys())
differences = evindenced_lexical_rules.difference(treebank_rules)
bad_generations = len(differences)
log("Found {0} bad generations ({1})".format(bad_generations, differences), 3)
#bad_parse_prob = 1 if prob == 0 else 0
#log("Scored {0} for prob {1}".format(bad_parse_prob, prob), 3)
bad_tag_problems = num_tag_problems(tree)
log("Found {0} X or FRAG tags".format(bad_tag_problems), 3)
bad_sbar_problems = num_sbar_problems(tree)
log("Found {0} bad SBAR issues".format(bad_sbar_problems), 3)
total_problems = bad_sbar_problems + bad_tag_problems + bad_generations
log("In '{0}'".format(sentence), 2)
log("Found {0} sentence formation problems".format(total_problems), 1)
sentence_probs.append(total_problems)
return sentence_probs
def parse(text, use_cache=True):
num_agrees = 0
num_not_agrees = 0
num_unsure = 0
lines = text.split("\n")
for line in lines:
sentences = sentence_tokenizer.parse(line, use_cache=use_cache)
for sentence in sentences:
line_agreements, line_non_agreements, line_unsure = 0, 0, 0
# Possession seems to be tricky for the parser, so we fudge
# a little here
sentence = sentence.replace("'s", '')
if sentence[-1] != ".":
sentence += "."
if use_cache:
cache_rs = cache_utils.cache_get('sub_verb_agreement',
sentence)
if cache_rs:
line_agreements, line_non_agreements, line_unsure = cache_rs
num_agrees += line_agreements
num_not_agrees += line_non_agreements
num_unsure += line_unsure
continue
log("Looking for Sub-Verb agreement in '%s'" % (sentence, ), 1)
tree = parsers.parse(sentence)[0]
dependencies = parsers.dependences(sentence)
sub_verb_deps = [
dep for dep in dependencies if dep['dep_name'] == 'nsubj'
]
if len(sub_verb_deps) == 0:
log("Couldn't find Subject-Verb dependency info", 1)
cache_utils.cache_set('sub_verb_agreement', sentence,
(0, 0, 0))
continue
for sub_verb in sub_verb_deps:
first_node = node_in_tree(tree, sub_verb['first_word'])
sec_node = node_in_tree(tree, sub_verb['second_word'])
if first_node and sec_node:
log("First Dep Node: %s" % (first_node, ), 2)
log("Sec Dep Node: %s" % (sec_node, ), 2)
try:
is_agreement = check_node_agreement(
first_node, sec_node)
if is_agreement:
line_agreements += 1
else:
line_non_agreements += 1
log("Agreement in sentence? %s" % (is_agreement, ), 1)
except Exception as e:
line_unsure += 1
log("Error looking for agreement? %s" % (e.message, ),
2)
# No agreement in pair. Not sure how to handle.
# More exhaustive search?
if use_cache:
cache_utils.cache_set(
'sub_verb_agreement', sentence,
(line_agreements, line_non_agreements, line_unsure))
num_agrees += line_agreements
num_not_agrees += line_non_agreements
num_unsure += line_unsure
return num_agrees, num_not_agrees, num_unsure
def parse(text):
# Strip numbers out, since that seems to cause problems for my approach
text = re.sub(r'\d+ ?', 'some ', text)
sentences = sentence_tokenizer.parse(text)
sentence_pronouns = []
for sentence in sentences:
log("Looking for pronouns in '{0}'".format(sentence), 2)
pronoun_totals = [[], [], []]
tree = parsers.parse(sentence)[0]
pronoun_trees = tree.subtrees(lambda x: x.node in pronoun_tags)
for pronoun_tree in pronoun_trees:
# First total up all the first person pronouns
for i in range(3):
if pronoun_tree[0].lower() in pronouns[i]:
pronoun_totals[i].append(pronoun_tree[0])
log("First Person '{0}'".format(pronoun_totals[0]), 3)
log("Second Person '{0}'".format(pronoun_totals[1]), 3)
log("Third Person '{0}'".format(pronoun_totals[2]), 3)
sentence_pronouns.append(pronoun_totals)
log("Pronouns found in text: %s" % (sentence_pronouns), 2)
# If there are 3rd person pronouns in any sentence, we have to decide
# if they are used correctly. We do this in the following, very
# expensive, but possibly correct manner.
#
# Start from the top down
# 1. Look back 2 sentences and see if we can find a refernece.
# IF NOT - its an error and do no more
# 2. If so, replace the refereneced word with "RUNNING"
# and search again, to see if there is a previous word it could refer
# to.
# IF NOT, its correct. Replace the pronoun with the referenced word
# and continue
# 3. Else, its not felicitous. Give bad credit
for i in range(len(sentences)):
if len(sentence_pronouns[i][2]) > 0:
pronoun_results = []
for third_pronoun in sentence_pronouns[i][2]:
all_sentences = sentences[max(0, i - 2):i + 1]
norm_sentences = ". ".join(
[a_sen.strip(".") for a_sen in all_sentences]) + "."
log(
"Looking for pronoun coherence for '{0}'".format(
norm_sentences), 4)
pronouns_refs = parsers.parse_coref(norm_sentences)
log("Recieved co-references {0}".format(pronouns_refs), 5)
found_bundle = False
for j in range(len(pronouns_refs)):
if third_pronoun == pronouns_refs[j]['pronoun']:
found_bundle = pronouns_refs[j]
break
if not found_bundle:
log("Found NO anticedent for {0}".format(third_pronoun), 3)
pronoun_results.append((third_pronoun, -1))
else:
log("Found anticedent for {0}".format(third_pronoun), 3)
ref_index = int(found_bundle['ref_sentence']) - 1 + (i - 2)
sentences[ref_index] = sentences[ref_index].replace(
found_bundle['ref'], 'RUNNING')
log(
"Replacing '{0}' with 'RUNNING'".format(
found_bundle['ref']), 3)
altered_sentences = sentences[max(0, i - 2):i + 1]
norm_altered_sentences = ". ".join(
[a_sen.strip(".")
for a_sen in altered_sentences]) + "."
log(
"New test sentences are '{0}'".format(
norm_altered_sentences), 4)
altered_pronouns_refs = parsers.parse_coref(
norm_altered_sentences)
if third_pronoun not in [
a_ref['pronoun'] for a_ref in altered_pronouns_refs
]:
log("Anticedent is unambigious!", 3)
pro_index = int(
found_bundle['pronoun_sentence']) - 1 + (i - 2)
sentences[pro_index] = sentences[pro_index].replace(
found_bundle['pronoun'], found_bundle['ref'])
pronoun_results.append(
(third_pronoun, found_bundle['ref']))
else:
log("Anticedent is ambigious", 3)
log("New Sentences: {0}".format(altered_pronouns_refs),
4)
pronoun_results.append((third_pronoun, .5))
sentence_pronouns[i][2] = pronoun_results
return sentence_pronouns
def parse(text):
# Strip numbers out, since that seems to cause problems for my approach
text = re.sub(r'\d+ ?', 'some ', text)
sentences = sentence_tokenizer.parse(text)
sentence_pronouns = []
for sentence in sentences:
log("Looking for pronouns in '{0}'".format(sentence), 2)
pronoun_totals = [[], [], []]
tree = parsers.parse(sentence)[0]
pronoun_trees = tree.subtrees(lambda x: x.node in pronoun_tags)
for pronoun_tree in pronoun_trees:
# First total up all the first person pronouns
for i in range(3):
if pronoun_tree[0].lower() in pronouns[i]:
pronoun_totals[i].append(pronoun_tree[0])
log("First Person '{0}'".format(pronoun_totals[0]), 3)
log("Second Person '{0}'".format(pronoun_totals[1]), 3)
log("Third Person '{0}'".format(pronoun_totals[2]), 3)
sentence_pronouns.append(pronoun_totals)
log("Pronouns found in text: %s" % (sentence_pronouns), 2)
# If there are 3rd person pronouns in any sentence, we have to decide
# if they are used correctly. We do this in the following, very
# expensive, but possibly correct manner.
#
# Start from the top down
# 1. Look back 2 sentences and see if we can find a refernece.
# IF NOT - its an error and do no more
# 2. If so, replace the refereneced word with "RUNNING"
# and search again, to see if there is a previous word it could refer
# to.
# IF NOT, its correct. Replace the pronoun with the referenced word
# and continue
# 3. Else, its not felicitous. Give bad credit
for i in range(len(sentences)):
if len(sentence_pronouns[i][2]) > 0:
pronoun_results = []
for third_pronoun in sentence_pronouns[i][2]:
all_sentences = sentences[max(0, i - 2):i + 1]
norm_sentences = ". ".join([a_sen.strip(".") for a_sen in all_sentences]) + "."
log("Looking for pronoun coherence for '{0}'".format(norm_sentences), 4)
pronouns_refs = parsers.parse_coref(norm_sentences)
log("Recieved co-references {0}".format(pronouns_refs), 5)
found_bundle = False
for j in range(len(pronouns_refs)):
if third_pronoun == pronouns_refs[j]['pronoun']:
found_bundle = pronouns_refs[j]
break
if not found_bundle:
log("Found NO anticedent for {0}".format(third_pronoun), 3)
pronoun_results.append((third_pronoun, -1))
else:
log("Found anticedent for {0}".format(third_pronoun), 3)
ref_index = int(found_bundle['ref_sentence']) - 1 + (i - 2)
sentences[ref_index] = sentences[ref_index].replace(found_bundle['ref'], 'RUNNING')
log("Replacing '{0}' with 'RUNNING'".format(found_bundle['ref']), 3)
altered_sentences = sentences[max(0, i - 2):i + 1]
norm_altered_sentences = ". ".join([a_sen.strip(".") for a_sen in altered_sentences]) + "."
log("New test sentences are '{0}'".format(norm_altered_sentences), 4)
altered_pronouns_refs = parsers.parse_coref(norm_altered_sentences)
if third_pronoun not in [a_ref['pronoun'] for a_ref in altered_pronouns_refs]:
log("Anticedent is unambigious!", 3)
pro_index = int(found_bundle['pronoun_sentence']) - 1 + (i - 2)
sentences[pro_index] = sentences[pro_index].replace(found_bundle['pronoun'], found_bundle['ref'])
pronoun_results.append((third_pronoun, found_bundle['ref']))
else:
log("Anticedent is ambigious", 3)
log("New Sentences: {0}".format(altered_pronouns_refs), 4)
pronoun_results.append((third_pronoun, .5))
sentence_pronouns[i][2] = pronoun_results
return sentence_pronouns
def parse(text, use_cache=True):
num_agrees = 0
num_not_agrees = 0
num_unsure = 0
lines = text.split("\n")
for line in lines:
sentences = sentence_tokenizer.parse(line, use_cache=use_cache)
for sentence in sentences:
line_agreements, line_non_agreements, line_unsure = 0, 0, 0
# Possession seems to be tricky for the parser, so we fudge
# a little here
sentence = sentence.replace("'s", '')
if sentence[-1] != ".":
sentence += "."
if use_cache:
cache_rs = cache_utils.cache_get('sub_verb_agreement', sentence)
if cache_rs:
line_agreements, line_non_agreements, line_unsure = cache_rs
num_agrees += line_agreements
num_not_agrees += line_non_agreements
num_unsure += line_unsure
continue
log("Looking for Sub-Verb agreement in '%s'" % (sentence,), 1)
tree = parsers.parse(sentence)[0]
dependencies = parsers.dependences(sentence)
sub_verb_deps = [dep for dep in dependencies if dep['dep_name'] == 'nsubj']
if len(sub_verb_deps) == 0:
log("Couldn't find Subject-Verb dependency info", 1)
cache_utils.cache_set('sub_verb_agreement', sentence, (0, 0, 0))
continue
for sub_verb in sub_verb_deps:
first_node = node_in_tree(tree, sub_verb['first_word'])
sec_node = node_in_tree(tree, sub_verb['second_word'])
if first_node and sec_node:
log("First Dep Node: %s" % (first_node,), 2)
log("Sec Dep Node: %s" % (sec_node,), 2)
try:
is_agreement = check_node_agreement(first_node, sec_node)
if is_agreement:
line_agreements += 1
else:
line_non_agreements += 1
log("Agreement in sentence? %s" % (is_agreement,), 1)
except Exception as e:
line_unsure += 1
log("Error looking for agreement? %s" % (e.message,), 2)
# No agreement in pair. Not sure how to handle.
# More exhaustive search?
if use_cache:
cache_utils.cache_set('sub_verb_agreement', sentence, (line_agreements, line_non_agreements, line_unsure))
num_agrees += line_agreements
num_not_agrees += line_non_agreements
num_unsure += line_unsure
return num_agrees, num_not_agrees, num_unsure
