def _add_tlinks_to_fragment(self, in_fragment, tmp_fragment, out_fragment):
"""Take the links from the merged tlinks and add them into the
fragment. Based on the method with the same name in the
classifier wrapper."""
xmldoc1 = Parser().parse_file(open(in_fragment,'r'))
xmldoc2 = Parser().parse_file(open(tmp_fragment,'r'))
xmldoc1.remove_tags(TLINK)
for tlink in xmldoc2.get_tags(TLINK):
reltype = tlink.attrs[RELTYPE]
id1 = tlink.attrs.get(EVENT_INSTANCE_ID, None)
if not id1:
id1 = tlink.attrs.get(TIME_ID, None)
if not id1:
logger.warn("Could not find id1 in " + tlink.content)
id2 = tlink.attrs.get(RELATED_TO_EVENT_INSTANCE, None)
if not id2:
id2 = tlink.attrs.get(RELATED_TO_TIME, None)
if not id2:
logger.warn("Could not find id2 in " + tlink.content)
#origin = CLASSIFIER + ' ' + tlink.attrs.get(CONFIDENCE,'')
origin = tlink.attrs.get('origin','')
xmldoc1.add_tlink(reltype, id1, id2, origin)
xmldoc1.save_to_file(out_fragment)
def _add_tlinks_to_fragment(self, in_fragment, tmp_fragment, out_fragment):
"""Takes the links created by the classifier and merges them into the
input fragment."""
xmldoc1 = Parser().parse_file(open(in_fragment, 'r'))
xmldoc2 = Parser().parse_file(open(tmp_fragment, 'r'))
for tlink in xmldoc2.get_tags(TLINK):
reltype = tlink.attrs[RELTYPE]
id1 = tlink.attrs.get(EVENT_INSTANCE_ID, None)
if not id1:
id1 = tlink.attrs.get(TIME_ID, None)
if not id1:
logger.warn("Could not find id1 in " + tlink.content)
id2 = tlink.attrs.get(RELATED_TO_EVENT_INSTANCE, None)
if not id2:
id2 = tlink.attrs.get(RELATED_TO_TIME, None)
if not id2:
logger.warn("Could not find id2 in " + tlink.content)
origin = CLASSIFIER + ' ' + tlink.attrs.get(CONFIDENCE, '')
xmldoc1.add_tlink(reltype, id1, id2, origin)
xmldoc1.save_to_file(out_fragment)
def _add_tlinks_to_fragment(self, in_fragment, tmp_fragment, out_fragment):
"""Takes the links created by the classifier and merges them into the
input fragment."""
xmldoc1 = Parser().parse_file(open(in_fragment,'r'))
xmldoc2 = Parser().parse_file(open(tmp_fragment,'r'))
for tlink in xmldoc2.get_tags(TLINK):
reltype = tlink.attrs[RELTYPE]
id1 = tlink.attrs.get(EVENT_INSTANCE_ID, None)
if not id1:
id1 = tlink.attrs.get(TIME_ID, None)
if not id1:
logger.warn("Could not find id1 in " + tlink.content)
id2 = tlink.attrs.get(RELATED_TO_EVENT_INSTANCE, None)
if not id2:
id2 = tlink.attrs.get(RELATED_TO_TIME, None)
if not id2:
logger.warn("Could not find id2 in " + tlink.content)
origin = CLASSIFIER + ' ' + tlink.attrs.get(CONFIDENCE,'')
xmldoc1.add_tlink(reltype, id1, id2, origin)
xmldoc1.save_to_file(out_fragment)
class HtmlGenerator:
"""An HtmlGenerator is created for an XML file with TimeML tags. It is
used to create HTML files that display the text with events and
times highlighted and links lined up with the sentences. It can
also be used to create tables for events, times and links.
Instance variables:
file_name - an absolute path
xmldoc - an XmlDocument
sentences - a list
instances - a mapping from eiid and eid to XmlDocElements that contain an instance
links - a mapping from eids and tids to links that contain them"""
def __init__(self, file_name):
self.file_name = file_name
file = open(file_name, 'r')
self.xmldoc = Parser().parse_file(file)
self.sentences = []
self.instance_idx = {}
self.event_idx = {}
self.timex_idx = {}
self.events = []
self.timexes = []
self.links = {}
self._init_sentence_list()
self._init_indexes()
self._init_events_list()
self._init_timexes_list()
self._init_link_index()
def _init_sentence_list(self):
"""Fill in the self.sentences list. Sentences do not include their
opening and closing tags."""
for open_s_tag in self.xmldoc.get_tags('s'):
close_s_tag = open_s_tag.get_closing_tag()
elements = open_s_tag.get_slice_till(close_s_tag.id)
self.sentences.append(Sentence(elements))
def _init_events_list(self):
for event in self.xmldoc.get_tags('EVENT'):
eid = event.attrs['eid']
instance = self.instance_idx[eid]
self.events.append(Event(event, instance))
def _init_timexes_list(self):
self.timexes = self.xmldoc.get_tags('TIMEX3')
def _init_indexes(self):
"""The value for these indixes are always XML elements."""
for instance in self.xmldoc.get_tags('MAKEINSTANCE'):
eiid = instance.attrs.get('eiid')
eid = instance.attrs.get('eventID')
self.instance_idx[eiid] = instance
self.instance_idx[eid] = instance
for event in self.xmldoc.get_tags('EVENT'):
eid = event.attrs.get('eid')
self.event_idx[eid] = event
for timex in self.xmldoc.get_tags('TIMEX3'):
tid = timex.attrs.get('tid')
self.timex_idx[tid] = timex
# need to add dct, but this needs to be done differently
self.timex_idx['t0'] = create_dct_element('20080515')
def _init_link_index(self):
link_elements = \
self.xmldoc.get_tags('ALINK') + \
self.xmldoc.get_tags('SLINK') + \
self.xmldoc.get_tags('TLINK')
for link_element in link_elements:
link = Link(link_element, self.instance_idx)
id = link.get_id(['eventInstanceID', 'timeID'])
try:
self.links[id].append(link)
except KeyError:
self.links[id] = [link]
def create_file(self, outfile, creators):
"""Creates a file with all sentences and the links lined up with the
sentences."""
fh = open(outfile, 'w')
fh.write("<html>\n<head><style>\n" +
"s {display: block; text-decoration: none}\n" +
"</style>\n<body>\n" + "<table cellpadding=4" +
"<tr>\n <td>source\n <td>%s\n" % self.file_name +
"<tr>\n <td>components\n <td>%s\n" % ' + '.join(creators) +
"</table>\n\n" + "<hr>\n\n" + "<table cellspacing=7pt>\n")
for sentence in self.sentences:
fh.write("\n<tr>\n <td>")
sentence.print_html(fh)
fh.write(" <td>")
for id in sentence.get_ids():
links = self.links.get(id, [])
for link in links:
if link.creator in creators:
fh.write(' ' + link.convert() + "<br/>\n")
fh.write("\n</table>\n</body>\n</html>\n")
def create_events_table(self, file):
fh = open(file, 'w')
fh.write("<html>\n<body>\n<table cellpadding=4>\n" +
"<tr align=\"left\">\n" +
" <th bgcolor=\"#dddddd\">event\n" +
" <th bgcolor=\"#dddddd\">pos\n" +
" <th bgcolor=\"#dddddd\">class\n" +
" <th bgcolor=\"#dddddd\">tense\n" +
" <th bgcolor=\"#dddddd\">aspect\n" +
" <th bgcolor=\"#dddddd\">polarity\n" +
" <th bgcolor=\"#dddddd\">modality\n" + "</tr>\n")
celltag = '<td bgcolor="#dddddd">'
for event in self.events:
fh.write("<tr>\n")
eid = event.attrs['eid']
text = event.attrs['text']
pos = event.attrs['pos'].lower()
eclass = event.attrs['class'].lower()
tense = event.attrs['tense'].lower()
aspect = event.attrs['aspect'].lower()
polarity = event.attrs['polarity'].lower()
modality = event.attrs.get('modality', '').lower()
if tense == 'none': tense = ''
if aspect == 'none': aspect = ''
if polarity == 'pos': polarity = ''
if aspect == 'perfective_progressive': aspect = 'perf_prog'
fh.write(" %s<font color=red>%s_%s</font>\n" %
(celltag, text, eid))
fh.write(" %s%s\n" % (celltag, pos))
fh.write(" %s%s\n" % (celltag, eclass))
fh.write(" %s%s\n" % (celltag, tense))
fh.write(" %s%s\n" % (celltag, aspect))
fh.write(" %s%s\n" % (celltag, polarity))
fh.write(" %s%s\n" % (celltag, modality))
fh.write("</table>\n</body>\n<html>\n")
def create_timexes_table(self, file):
fh = open(file, 'w')
fh.write("<html>\n<body>\n<table cellpadding=4>\n" +
"<tr align=\"left\">\n" +
" <th bgcolor=\"#dddddd\">timex\n" +
" <th bgcolor=\"#dddddd\">type\n" +
" <th bgcolor=\"#dddddd\">value\n" + "</tr>\n")
celltag = '<td bgcolor="#dddddd">'
for timex in self.timexes:
fh.write("<tr>\n")
tid = timex.attrs['tid']
text = timex.collect_content()
type = timex.attrs['TYPE'].lower()
value = timex.attrs.get('VAL')
fh.write(" %s<font color=blue>%s_%s</font>\n" %
(celltag, text, tid))
fh.write(" %s%s\n" % (celltag, type))
fh.write(" %s%s\n" % (celltag, str(value)))
fh.write("</table>\n</body>\n<html>\n")
def create_links_table(self, file):
fh = open(file, 'w')
fh.write("<html>\n<body>\n<table cellpadding=4>\n")
celltag = '<td bgcolor="#dddddd">'
for sentence in self.sentences:
for id in sentence.get_ids():
for link in self.links.get(id, []):
id1 = link.get_id1()
id2 = link.get_id2()
text1 = self._get_text(id1)
text2 = self._get_text(id2)
full_text1 = color_text(text1, id1)
full_text2 = color_text(text2, id2)
origin = link.attrs.get('origin')
if not origin:
origin = link.attrs.get('syntax')
fh.write("<tr>\n")
fh.write(" %s%s\n" % (celltag, full_text1))
fh.write(" %s%s\n" % (celltag, link.attrs['relType']))
fh.write(" %s%s\n" % (celltag, full_text2))
fh.write(" %s%s\n" % (celltag, origin))
fh.write("</tr>\n")
fh.write("</table>\n</body>\n<html>\n")
def _get_text(self, id):
# this is a bit of a hack and needs to be solved elsewhere
# the DCT has no tag and the cod eto collect data crashes
if id == 't0':
return 'DCT'
if id.startswith('t'):
timex = self.timex_idx[id]
return timex.collect_content()
if id.startswith('e'):
instance = self.instance_idx[id]
eid = instance.attrs['eventID']
event = self.event_idx[eid]
return event.collect_content()
def tlink_inject_with_prior_with_check(no_tlink_file, result_file, tlink_file,
original_file):
"""
"""
"""
Verb event should be a dictionary to map between
an event id and some other lemmas generated from the
initial lemma.
"""
verb_events = {}
"""
EVENT tag sample
<EVENT class="OCCURRENCE" eid="e1000028">
"""
xml_document = Parser().parse_file(open(no_tlink_file, "r"))
xmldoc_original = Parser().parse_file(open(original_file, "r"))
for element in xml_document.get_tags(EVENT):
if element.is_opening_tag():
eid = element.attrs[EID]
event_content = element.next.content
synsets_event = None
if len(wn.synsets(event_content, 'v')) > 0:
synsets_event = wn.synsets(element.next.content,
'v')[0].lemma_names
verb_morphy = wn.morphy(event_content, 'v')
verb_events[eid] = {
MORPHY_LEMMA: verb_morphy,
SYNSET_LEMMA: synsets_event
}
"""
<MAKEINSTANCE eventID="e2" polarity="POS" pos="VERB" eiid="ei2"
tense="PRESENT" aspect="PERFECTIVE">
"""
verb_event_instance = {}
for element in xml_document.get_tags(INSTANCE):
if element.is_opening_tag():
eiid = element.attrs[EIID]
eid = element.attrs[EVENTID]
if eid in verb_events:
verb_event_instance[eiid] = verb_events[eid]
"""
All TLINKs in the original document between two events
Because excepts the TLINKs parts, original and classified
documents should be identical, so they could use the same
verb_event_instance.
"""
original_ee_tlinks = {}
for element in xmldoc_original.get_tags(TLINK):
# keep track of event order here
if element.is_opening_tag():
lid = element.attrs[LID]
if EVENT_INSTANCE_ID in element.attrs:
eiid = element.attrs[EVENT_INSTANCE_ID]
if RELATED_TO_EVENT_INSTANCE in element.attrs:
reiid = element.attrs[RELATED_TO_EVENT_INSTANCE]
if RELTYPE in element.attrs:
if eiid in verb_event_instance and reiid in verb_event_instance:
original_ee_tlinks[(eiid, reiid)] = (
lid, element.attrs[RELTYPE])
with open(result_file, 'r') as result_file:
label_vote_dict = json.load(result_file)
fix_label_counter = 0
worsen_label_counter = 0
for feature_type in label_vote_dict:
for line_counter in label_vote_dict[feature_type]:
result_dict = label_vote_dict[feature_type][line_counter][
RESULT_DICT]
label_vote = label_vote_dict[feature_type][line_counter][VOTE_DICT]
ids = label_vote_dict[feature_type][line_counter][TLINK_IDS_DICT]
raw_relType = label_vote[-1][0]
"""
Have to re calculate the relType here
- Calculate P ( label | lemma_pair, result_vector ) ~ P(label)
x P ( result_vector | label )
x P ( lemma_pair | label )
"""
# if raw_relType == NORELATION or raw_relType == SIMULTANEOUS:
if raw_relType == NORELATION:
pass
else:
def check_event_pair(ids):
for id in ids:
if id[1] == TID:
return False
return True
"""
If the relation is between event pairs, we check
the narrative scheme, else, just use the raw_relType
for TLink between time and event.
"""
new_ids = {}
for id in ids:
if id[1] in [TID, EIID]:
new_ids[id[0]] = id[2]
original_relation = None
if (new_ids['0'], new_ids['1']) in original_ee_tlinks:
original_relation = original_ee_tlinks[(new_ids['0'],
new_ids['1'])][1]
elif (new_ids['1'], new_ids['0']) in original_ee_tlinks:
original_relation = reverse(
original_ee_tlinks[(new_ids['1'], new_ids['0'])][1])
"""
Eleventh try
Only consider main event pairs inter sentences
"""
if check_event_pair(ids):
probability = {}
max_label = None
max_prob = None
"""
Third approach: only consider labels inside the votes
"""
result_prob = {}
label_prob = {}
lemma_pair_prob = {}
for label in [str(label[0]) for label in label_vote]:
if not label in [BEFORE, AFTER, SIMULTANEOUS]:
continue
"""
15th try: only fix BEFORE and AFTER labels
"""
# if not label in [BEFORE, AFTER]:
# continue
# for label in [BEFORE, AFTER, SIMULTANEOUS]:
probability[label] = 1
result_prob[label] = histogram.get_probability_vector(
result_dict, label)
probability[label] *= result_prob[label]
"""
First approach: only use the morphy lemma
"""
morphy_1 = verb_event_instance[
new_ids['0']][MORPHY_LEMMA]
morphy_2 = verb_event_instance[
new_ids['1']][MORPHY_LEMMA]
# lemma_pair_prob[label] = crd.get_lemma_pair_prob((morphy_1,morphy_2,label))
# lemma_pair_prob[label] = crd.get_lemma_pair_prob_smoothing((morphy_1,morphy_2),label)
"""
Tenth approach: desperate try, multiply all of them together
"""
# probability[label] *= lemma_pair_prob[label]
"""
Done first approach
"""
"""
Second approach: use all pairs of lemmas with lemma
in corresponding two synsets
"""
lemma_pair_prob[label] = 0
synset_1 = verb_event_instance[
new_ids['0']][SYNSET_LEMMA]
synset_2 = verb_event_instance[
new_ids['1']][SYNSET_LEMMA]
if synset_1 != None and synset_2 != None:
for l_1, l_2 in itertools.product(
synset_1, synset_2):
lemma_pair_prob[
label] += crd.get_lemma_pair_prob_smoothing(
(l_1, l_2), label)
# lemma_pair_prob[label] += crd.get_lemma_pair_prob((l_1,l_2),label)
"""
Done second approach
"""
"""
Seventh try: turn off lemma pairs
"""
probability[label] *= lemma_pair_prob[label]
label_prob[label] = histogram.get_probability_label(
label)
# """
# 14th try: normalize BEFORE and AFTER labels
# """
# if label == BEFORE or label == AFTER:
# label_prob[label] = (histogram.get_probability_label (BEFORE)
# + histogram.get_probability_label (AFTER))/2
"""
13 rd try: disable label prob
"""
probability[label] *= label_prob[label]
if max_prob == None or max_prob < probability[label]:
max_prob = probability[label]
max_label = label
"""
Forth try:
if max_prob == 0, it means that all probabilities = 0
and we should follow the initialy vote
"""
if max_prob == 0:
relType = raw_relType
else:
relType = max_label
need_to_keep_track = False
if (relType == raw_relType and original_relation != None
and original_relation != relType
and original_relation
in [BEFORE, AFTER, SIMULTANEOUS]):
need_to_keep_track = True
logging.info(
'---------------DOESNT HELP----------------')
if relType != raw_relType and original_relation != None:
need_to_keep_track = True
if (original_relation == relType):
fix_label_counter += 1
if (original_relation == raw_relType):
worsen_label_counter += 1
logging.info(
'---------------MAKE CHANGE----------------')
if need_to_keep_track:
logging.info('Correct relation : %s' %
original_relation)
logging.info('Original classified : %s' % raw_relType)
logging.info('Prior classified : %s' % relType)
logging.info(morphy_1)
logging.info(morphy_2)
logging.info(synset_1)
logging.info(synset_2)
logging.info('--result_prob--')
logging.info(result_prob)
logging.info('--label_prob--')
logging.info(label_prob)
logging.info('--lemma_pair_prob--')
logging.info(lemma_pair_prob)
logging.info(probability)
logging.info('==============================')
else:
relType = raw_relType
xml_document.add_tlink(relType, new_ids['0'], new_ids['1'],
SVM_CLASSIFIER_ORIGIN)
xml_document.save_to_file(tlink_file)
return (fix_label_counter, worsen_label_counter)
class Blinker (TarsqiComponent):
"""Implements the Blinker component of Tarsqi. Blinker takes the
shallow tree implemented in the Document object and applies rules
that capture regularities between events and times as well as
between events.
Instance variables:
NAME - a string
rules - a BlinkerRuleDictionary
rule2_index - a dictionary, quick access to type 2 rules
dct - a string of the form YYYYMMDD, representing the document creation time
xmldoc - an XmlDocument, created by xml_parser.Parser
doctree - a Document, created by converter.FragmentConverter"""
def __init__(self):
"""Set component name and load rules into a BlinkerRuleDictionary
object, this object knows where the rules are stored."""
self.NAME = BLINKER
self.rules = BlinkerRuleDictionary()
self.rule2_index = {}
#self.rules.pp_ruletype(2)
self._populate_rule2_index()
def _populate_rule2_index(self):
"""Rules of type 2 (timex-signal-event) can be simply put in a
hash keyed on the signals."""
for rule in self.rules[2]:
relation = rule.get_attribute('relation')[0] # vals are now lists
signal = rule.get_attribute('signal')[0]
self.rule2_index[signal] = relation
def process(self, infile, outfile, dct):
"""Apply all Blinker rules to the input file. Parses the xml
file with xml_parser.Parser and converts it to a shallow tree
with converter.FragmentConverter. Then applies the Blinker
rules. Curently only applies rules of type 2.
Arguments
infile - an absolute path
outfile - an absolute path
No return value."""
xmlfile = open(infile, "r")
self.dct = dct
self.xmldoc = Parser().parse_file(xmlfile)
self.doctree = FragmentConverter(self.xmldoc, infile).convert(user=BLINKER)
#self.print_doctree(BLINKER)
self._run_blinker()
self.xmldoc.save_to_file(outfile)
def _run_blinker(self):
"""Apply BLinker rules to the sentences in the doctree
variable. Currently only deals with rule type 2, anchoring an
event to a timex in those cases where there is a signal (that
is, a preposition) available. New Tlinks are added just before
the closing tag of the fragment."""
self._run_timex_linking()
self._apply_event_ordering_with_signal_rules()
# variables needed for different rule types are prefixed with r<ruleNum>
r3_event1 = None
# iterate over sentences
for si in range(len(self.doctree)):
sentence = self.doctree[si]
r3_main_event = None
if _DEBUG5: print "processing sentence", si
# iterate over elements within a sentence
for i in range(len(sentence)):
element = sentence[i]
timex = element.get_timex()
event = element.get_event()
# RULE TYPE 2
if timex:
# chunk contains a timex, now try to anchor events to it
self._apply_event_anchoring_rules(sentence, timex, i)
# RULE TYPE 3
if event and element.isChunk() and element.isVerbChunk():
# the first verb event in a sentence is considered the main event
if not r3_main_event:
r3_main_event = event
# if previous sentence contained an event, create a link
if r3_event1:
r3_event2 = r3_main_event
self._apply_type3_rules(r3_event1, r3_event2)
r3_event1 = r3_event2
# else set event1
else:
r3_event1 = r3_main_event
#"""
# RULE TYPE 5
if event and element.isChunk() \
and element.isVerbChunk() \
and event.attrs['class'] == 'REPORTING':
if _DEBUG5:
print "applying type 5 rules"
self._apply_type5_rules(sentence, event, i)
#"""
# R3: if no main event in sentence
if not r3_main_event:
r3_event1 = None
def _run_timex_linking(self):
"""Apply the rules that govern relations between TIMEX3 tags. Only
applies to TIMEX3 tags with a VAL attribute equal to DATE."""
timexes = [timex for timex in self.xmldoc.get_tags(TIMEX)
if timex.attrs['TYPE'] == 'DATE']
for t in timexes:
if t.attrs.get('VAL', None) is None:
logger.warn("Missing VAL: %s" % t.get_content())
for i in range(len(timexes)):
for j in range(len(timexes)):
if i < j:
try:
self._create_timex_link(timexes[i], timexes[j])
except Exception:
logger.error("Error in Timex Linking:\n%s\n%s" % \
(timexes[i].get_content(),
timexes[j].get_content()))
def _create_timex_link(self, timex1, timex2):
"""Try to create a TLINK between two timexes."""
creation_year = self.dct[0:4]
date1 = timex1.attrs.get('VAL', None)
date2 = timex2.attrs.get('VAL', None)
if date1 is None or date2 is None:
return
date1 = fix_timex_val(date1)
date2 = fix_timex_val(date2)
tid1 = timex1.attrs['tid']
tid2 = timex2.attrs['tid']
comment = "Blinker - Timex Linking"
if date1 == date2:
if date1 not in ('PAST_REF', 'FUTURE_REF'):
self.xmldoc.add_tlink('IDENTITY', tid1, tid2, comment)
else:
rel = compare_date(date1, date2, creation_year)
if rel != 'IDENTITY':
self.xmldoc.add_tlink(rel, tid1, tid2, comment)
def _apply_type3_rules(self, event1, event2):
""" Creates a TLINK between two main events """
if _DEBUG3:
print event1.dtrs[0].getText(), event2.dtrs[0].getText()
print event1.dtrs[0].getText(), event1.attrs['class'], \
event1.attrs['tense'], event1.attrs['aspect']
print event2.dtrs[0].getText(), event2.attrs['class'], \
event2.attrs['tense'], event2.attrs['aspect']
for i in range(len(self.rules[3])):
rule = self.rules[3][i]
if _DEBUG3:
print "RULE %s:" % (rule.rule_number)
print rule.attrs['arg1.class'], rule.attrs['arg1.tense'], rule.attrs['arg1.aspect']
print rule.attrs['arg2.class'], rule.attrs['arg2.tense'], rule.attrs['arg2.aspect']
# see tags.py and library.timeMLspec.py for attribute names
if event1.attrs['class'] in rule.attrs['arg1.class'] and \
event2.attrs['class'] in rule.attrs['arg2.class'] and \
event1.attrs['tense'] in rule.attrs['arg1.tense'] and \
event2.attrs['tense'] in rule.attrs['arg2.tense'] and \
event1.attrs['aspect'] in rule.attrs['arg1.aspect'] and \
event2.attrs['aspect'] in rule.attrs['arg2.aspect']:
rel = rule.attrs['relation'][0]
self.xmldoc.add_tlink( rel,
event1.attrs[EIID],
event2.attrs[EIID],
"Blinker - Type 3 (rule %s)" % rule.rule_number)
if _DEBUG3: print "RULE %s fired!" % rule.rule_number
# apply the first matching rule
return
def _apply_type5_rules(self, sentence, event1, position):
""" Creates TLINKs between the reporting event and reported events
Takes as arguments sentence, reporting event constituent, and
position of that constituent within the sentence list"""
# filter out rules with wrong tense
applicable_rules = self.rules[5][:]
applicable_rules = [rule for rule in applicable_rules
if event1.attrs['tense'] in rule.attrs['arg1.tense']]
# reset to opposite when quote is encountered
direct = 'INDIRECT'
# forward
if _DEBUG5:
print "inside rule application function"
sentence.pretty_print()
for i in range(position+1, len(sentence)):
if _DEBUG5: print "processing element", i
element = sentence[i]
# quote
if element.isToken() and element.getText() in QUOTES:
if direct == 'DIRECT': direct = 'INDIRECT'
if direct == 'INDIRECT': direct = 'DIRECT'
# event
event2 = element.get_event()
if event2 and element.isChunk() and element.isVerbChunk():
current_rules = applicable_rules[:]
current_rules = [rule for rule in current_rules if direct in rule.attrs['sentType']]
if _DEBUG5:
print event1.dtrs[0].getText(), event2.dtrs[0].getText()
print event1.dtrs[0].getText(), event1.attrs['class'], \
event1.attrs['tense'], event1.attrs['aspect']
print event2.dtrs[0].getText(), event2.attrs['class'], \
event2.attrs['tense'], event2.attrs['aspect']
for rule in current_rules:
# if attribute not set in the rule, accept any value
for att in ['class', 'tense', 'aspect']:
if not rule.attrs.has_key('arg2.'+att):
rule.attrs['arg2.'+att] = [event2.attrs[att]]
if _DEBUG5:
print "RULE %s (%s):" % (rule.rule_number, rule.attrs['sentType'][0])
print rule.attrs['arg1.class'], rule.attrs['arg1.tense'], \
rule.attrs['arg1.aspect']
print rule.attrs['arg2.class'], rule.attrs['arg2.tense'], \
rule.attrs['arg2.aspect']
# check that specified values match
if event2.attrs['class'] in rule.attrs['arg2.class'] and \
event2.attrs['tense'] in rule.attrs['arg2.tense'] and \
event2.attrs['aspect'] in rule.attrs['arg2.aspect']:
rel = rule.attrs['relation'][0]
self.xmldoc.add_tlink( rel,
event1.attrs['eiid'],
event2.attrs['eiid'],
"Blinker - Type 5 (rule %s)" % rule.rule_number)
if _DEBUG5: print "RULE %s fired!" % rule.rule_number
# apply the first matching rule
return
# backward
# - this creates multiple links for REPORTING to REPORTING
# - may add the appropriate rules to the rule file instead
direct = 'INDIRECT'
for i in range(position-1, -1, -1): # ..,3,2,1,0
if _DEBUG5: print "processing element", i
element = sentence[i]
# quote
if element.isToken() and element.getText() in QUOTES:
if direct == 'DIRECT': direct = 'INDIRECT'
if direct == 'INDIRECT': direct = 'DIRECT'
# event
event2 = element.get_event()
if event2 and element.isChunk() and element.isVerbChunk():
current_rules = applicable_rules[:]
current_rules = [rule for rule in current_rules if direct in rule.attrs['sentType']]
if _DEBUG5:
print event1.dtrs[0].getText(), event2.dtrs[0].getText()
print event1.dtrs[0].getText(), event1.attrs['class'], \
event1.attrs['tense'], event1.attrs['aspect']
print event2.dtrs[0].getText(), event2.attrs['class'], \
event2.attrs['tense'], event2.attrs['aspect']
print "Applying rules for sentence type:", direct, len(current_rules), "rules"
for rule in current_rules:
# if attribute not set in the rule, accept any value
for att in ['class', 'tense', 'aspect']:
if not rule.attrs.has_key('arg2.'+att):
rule.attrs['arg2.'+att] = [event2.attrs[att]]
if _DEBUG5:
print "RULE %s (%s):" % (rule.rule_number, rule.attrs['sentType'][0])
print rule.attrs['arg1.class'], rule.attrs['arg1.tense'], \
rule.attrs['arg1.aspect']
print rule.attrs['arg2.class'], rule.attrs['arg2.tense'], \
rule.attrs['arg2.aspect']
# check that specified values match
if event2.attrs['class'] in rule.attrs['arg2.class'] and \
event2.attrs['tense'] in rule.attrs['arg2.tense'] and \
event2.attrs['aspect'] in rule.attrs['arg2.aspect']:
rel = rule.attrs['relation'][0]
self.xmldoc.add_tlink( rel,
event1.attrs['eiid'],
event2.attrs['eiid'],
"Blinker - Type 5 (rule %s)" % rule.rule_number)
if _DEBUG5: print "RULE %s fired!" % rule.rule_number
# apply the first matching rule
return
def _apply_event_anchoring_rules(self, sentence, timex, i):
"""Anchor events to a given timex that occurs in the sentence
at index i. The method proceeds by looking for some simple
syntactic patterns with and without prepositions. If a pattern
with a preposition occurs, then the preposition is looked up
in self.rule2_index. If no signal is found, then the default
INCLUDES rule will apply (rule 1), this is not yet
implemented."""
# NOTES:
# - Need to add some kind of confidence measures
# PATTERN: [TIMEX EVENT]
# Or, more precisely, an event in the same chunk as the timex
# Example: "October elections"
event = sentence[i].get_event()
if event:
eiid = event.attrs[EIID]
tid = timex.attrs[TID]
self.xmldoc.add_tlink('IS_INCLUDED', eiid, tid, "Blinker - Type 1")
return
# Pattern: [CHUNK-WITH-EVENT] Prep [CHUNK-WITH-TIMEX]
if i > 1:
event = sentence[i-2].get_event()
if sentence[i-1].isPreposition() and event:
signal = sentence[i-1].getText().lower()
rel = self.rule2_index.get(signal)
eiid = event.attrs[EIID]
tid = timex.attrs[TID]
if _DEBUG2:
print "FOUND: [%s] %s [%s] --> %s" % \
(event.dtrs[0].getText(), signal, timex.getText(), rel)
self.xmldoc.add_tlink(rel, eiid, tid, "Blinker - Type 2 (%s)" % signal)
return
# Pattern: [CHUNK-WITH-VERBAL-EVENT] [CHUNK-WITH_TIMEX]
if i > 0:
previous_chunk = sentence[i-1]
if previous_chunk.isVerbChunk():
event = previous_chunk.get_event()
if event:
#if event.attrs[POL] != 'NEG':
eiid = event.attrs[EIID]
tid = timex.attrs[TID]
self.xmldoc.add_tlink('IS_INCLUDED', eiid, tid, "Blinker - Type 1a")
return
def _apply_event_ordering_with_signal_rules(self):
"""Some more rules without using any rules, basically a placeholder
for event ordering rules that use a signal."""
signal_mapping = {
'after': 'AFTER',
'before': 'BEFORE',
'during': 'DURING'
}
for si in range(len(self.doctree)):
sentence = self.doctree[si]
for i in range(len(sentence)):
try:
#print sentence[i:i+4]
(VG1, Prep, NG, VG2) = sentence[i:i+4]
event1 = VG1.get_event()
event2 = VG2.get_event()
# Pattern: [VG +Event] [Prep] [NG -Event] [VG +Event]
if event1 and VG1.isVerbChunk() and \
Prep.isPreposition() and \
NG.isNounChunk() and not NG.get_event() and \
event2 and VG2.isVerbChunk():
#print "[VG +Event] [Prep] [NG -Event] [VG +Event]"
#print Prep
prep_token = Prep.getText().lower()
#print prep_token
rel = signal_mapping.get(prep_token)
#print rel
if rel:
#print 'adding tlink'
eiid1 = event1.attrs[EIID]
eiid2 = event2.attrs[EIID]
self.xmldoc.add_tlink(rel, eiid1, eiid2, "Blinker - Event:Signal:Event")
except:
pass
class HtmlGenerator:
"""An HtmlGenerator is created for an XML file with TimeML tags. It is
used to create HTML files that display the text with events and
times highlighted and links lined up with the sentences. It can
also be used to create tables for events, times and links.
Instance variables:
file_name - an absolute path
xmldoc - an XmlDocument
sentences - a list
instances - a mapping from eiid and eid to XmlDocElements that contain an instance
links - a mapping from eids and tids to links that contain them"""
def __init__(self, file_name):
self.file_name = file_name
file = open(file_name,'r')
self.xmldoc = Parser().parse_file(file)
self.sentences = []
self.instance_idx = {}
self.event_idx = {}
self.timex_idx = {}
self.events = []
self.timexes = []
self.links = {}
self._init_sentence_list()
self._init_indexes()
self._init_events_list()
self._init_timexes_list()
self._init_link_index()
def _init_sentence_list(self):
"""Fill in the self.sentences list. Sentences do not include their
opening and closing tags."""
for open_s_tag in self.xmldoc.get_tags('s'):
close_s_tag = open_s_tag.get_closing_tag()
elements = open_s_tag.get_slice_till(close_s_tag.id)
self.sentences.append(Sentence(elements))
def _init_events_list(self):
for event in self.xmldoc.get_tags('EVENT'):
eid = event.attrs['eid']
instance = self.instance_idx[eid]
self.events.append(Event(event, instance))
def _init_timexes_list(self):
self.timexes = self.xmldoc.get_tags('TIMEX3')
def _init_indexes(self):
"""The value for these indixes are always XML elements."""
for instance in self.xmldoc.get_tags('MAKEINSTANCE'):
eiid = instance.attrs.get('eiid')
eid = instance.attrs.get('eventID')
self.instance_idx[eiid] = instance
self.instance_idx[eid] = instance
for event in self.xmldoc.get_tags('EVENT'):
eid = event.attrs.get('eid')
self.event_idx[eid] = event
for timex in self.xmldoc.get_tags('TIMEX3'):
tid = timex.attrs.get('tid')
self.timex_idx[tid] = timex
# need to add dct, but this needs to be done differently
self.timex_idx['t0'] = create_dct_element('20080515')
def _init_link_index(self):
link_elements = \
self.xmldoc.get_tags('ALINK') + \
self.xmldoc.get_tags('SLINK') + \
self.xmldoc.get_tags('TLINK')
for link_element in link_elements:
link = Link(link_element, self.instance_idx)
id = link.get_id(['eventInstanceID', 'timeID'])
try:
self.links[id].append(link)
except KeyError:
self.links[id] = [link]
def create_file(self, outfile, creators):
"""Creates a file with all sentences and the links lined up with the
sentences."""
fh = open(outfile, 'w')
fh.write(
"<html>\n<head><style>\n" +
"s {display: block; text-decoration: none}\n" +
"</style>\n<body>\n" +
"<table cellpadding=4" +
"<tr>\n <td>source\n <td>%s\n" % self.file_name +
"<tr>\n <td>components\n <td>%s\n" % ' + '.join(creators) +
"</table>\n\n" +
"<hr>\n\n" +
"<table cellspacing=7pt>\n" )
for sentence in self.sentences:
fh.write("\n<tr>\n <td>")
sentence.print_html(fh)
fh.write(" <td>")
for id in sentence.get_ids():
links = self.links.get(id,[])
for link in links:
if link.creator in creators:
fh.write(' ' + link.convert() + "<br/>\n")
fh.write("\n</table>\n</body>\n</html>\n")
def create_events_table(self, file):
fh = open(file,'w')
fh.write("<html>\n<body>\n<table cellpadding=4>\n" +
"<tr align=\"left\">\n" +
" <th bgcolor=\"#dddddd\">event\n" +
" <th bgcolor=\"#dddddd\">pos\n" +
" <th bgcolor=\"#dddddd\">class\n" +
" <th bgcolor=\"#dddddd\">tense\n" +
" <th bgcolor=\"#dddddd\">aspect\n" +
" <th bgcolor=\"#dddddd\">polarity\n" +
" <th bgcolor=\"#dddddd\">modality\n" +
"</tr>\n")
celltag = '<td bgcolor="#dddddd">'
for event in self.events:
fh.write("<tr>\n")
eid = event.attrs['eid']
text = event.attrs['text']
pos = event.attrs['pos'].lower()
eclass = event.attrs['class'].lower()
tense = event.attrs['tense'].lower()
aspect = event.attrs['aspect'].lower()
polarity = event.attrs['polarity'].lower()
modality = event.attrs.get('modality', '').lower()
if tense == 'none': tense = ''
if aspect == 'none': aspect = ''
if polarity == 'pos': polarity = ''
if aspect == 'perfective_progressive': aspect = 'perf_prog'
fh.write(" %s<font color=red>%s_%s</font>\n" % (celltag, text, eid))
fh.write(" %s%s\n" % (celltag, pos))
fh.write(" %s%s\n" % (celltag, eclass))
fh.write(" %s%s\n" % (celltag, tense))
fh.write(" %s%s\n" % (celltag, aspect))
fh.write(" %s%s\n" % (celltag, polarity))
fh.write(" %s%s\n" % (celltag, modality))
fh.write("</table>\n</body>\n<html>\n")
def create_timexes_table(self, file):
fh = open(file,'w')
fh.write("<html>\n<body>\n<table cellpadding=4>\n" +
"<tr align=\"left\">\n" +
" <th bgcolor=\"#dddddd\">timex\n" +
" <th bgcolor=\"#dddddd\">type\n" +
" <th bgcolor=\"#dddddd\">value\n" +
"</tr>\n")
celltag = '<td bgcolor="#dddddd">'
for timex in self.timexes:
fh.write("<tr>\n")
tid = timex.attrs['tid']
text = timex.collect_content()
type = timex.attrs['TYPE'].lower()
value = timex.attrs.get('VAL')
fh.write(" %s<font color=blue>%s_%s</font>\n" % (celltag, text, tid))
fh.write(" %s%s\n" % (celltag, type))
fh.write(" %s%s\n" % (celltag, str(value)))
fh.write("</table>\n</body>\n<html>\n")
def create_links_table(self, file):
fh = open(file,'w')
fh.write("<html>\n<body>\n<table cellpadding=4>\n")
celltag = '<td bgcolor="#dddddd">'
for sentence in self.sentences:
for id in sentence.get_ids():
for link in self.links.get(id,[]):
id1 = link.get_id1()
id2 = link.get_id2()
text1 = self._get_text(id1)
text2 = self._get_text(id2)
full_text1 = color_text(text1, id1)
full_text2 = color_text(text2, id2)
origin = link.attrs.get('origin')
if not origin:
origin = link.attrs.get('syntax')
fh.write("<tr>\n")
fh.write(" %s%s\n" % (celltag, full_text1))
fh.write(" %s%s\n" % (celltag, link.attrs['relType']))
fh.write(" %s%s\n" % (celltag, full_text2))
fh.write(" %s%s\n" % (celltag, origin))
fh.write("</tr>\n")
fh.write("</table>\n</body>\n<html>\n")
def _get_text(self, id):
# this is a bit of a hack and needs to be solved elsewhere
# the DCT has no tag and the cod eto collect data crashes
if id == 't0':
return 'DCT'
if id.startswith('t'):
timex = self.timex_idx[id]
return timex.collect_content()
if id.startswith('e'):
instance = self.instance_idx[id]
eid = instance.attrs['eventID']
event = self.event_idx[eid]
return event.collect_content()
def check_abnormal_single(tlink_file):
xml_document = Parser().parse_file(open(tlink_file, "r"))
ee_tlinks = []
"""
It doesn't ensure that any event that
has a TLINK with the dct time need to be
the main event in a sentence, but it's correct
for the classified tlinks.
"""
main_events = {}
for element in xml_document.get_tags(TLINK):
# keep track of event order here
if element.is_opening_tag():
if EVENT_INSTANCE_ID in element.attrs:
eid = element.attrs[EVENT_INSTANCE_ID]
if RELATED_TO_EVENT_INSTANCE in element.attrs:
reid = element.attrs[RELATED_TO_EVENT_INSTANCE]
if RELTYPE in element.attrs:
ee_tlinks.append((eid, reid, element.attrs[RELTYPE]))
if RELATED_TO_TIME in element.attrs:
rtid = element.attrs[RELATED_TO_TIME]
if RELTYPE in element.attrs:
if rtid == 't0':
"""
Reverse the relation and the position of
time and event so as the timeid is always
the main entity
"""
main_events[eid] = (reverse(
element.attrs[RELTYPE]))
if TIME_ID in element.attrs:
tid = element.attrs[TIME_ID]
if RELATED_TO_EVENT_INSTANCE in element.attrs:
reid = element.attrs[RELATED_TO_EVENT_INSTANCE]
if RELTYPE in element.attrs:
if tid == 't0':
main_events[reid] = (element.attrs[RELTYPE])
total_number = 0
wrong_number = 0
for ee_tlink in ee_tlinks:
if ee_tlink[0] in main_events and ee_tlink[1] in main_events:
total_number += 1
"""
They are all main events
Relations between main events: AFTER, BEFORE and SIMULTANEOUS
Relations between main event and dct time: AFTER, BEFORE and SIMULTANEOUS
"""
logging.info("=========================================")
logging.info(ee_tlink[0])
logging.info(ee_tlink[1])
"""
event 0 is main, related to dct time
"""
relation_1 = reverse(main_events[ee_tlink[0]])
logging.info(relation_1)
"""
dct time is main, related to event 1
"""
relation_2 = main_events[ee_tlink[1]]
logging.info(relation_2)
"""
event 0 is main, related to event 1
"""
relation_3 = ee_tlink[2]
logging.info(relation_3)
if relation_3 in LOGIC_COMPOSITION[(relation_1, relation_2)]:
logging.info("Satisfy constraint")
else:
wrong_number += 1
logging.warn("DOESN'T SATISFY")
logging.info("Wrong number %d/ Total %d" % (wrong_number, total_number))
return (wrong_number, total_number)
def compare_performance_single(tlink_file, original_file):
logging.info('================Compare======================')
logging.info('Classified file: %s' % tlink_file)
logging.info('Original file: %s' % original_file)
"""
Compare the performance of a classified file (that is the result of
any algorithm or method), toward a destination gold file and the
event pair temporal ordering provided by narrative scheme database.
Only compare the performance between classified files,
original files, and temporal ordering database with TLINKs
that is:
- TLINKS between two events.
- Two events need to appear in both original file
and classified file
- Two events need to be found in the narrative scheme.
"""
xmldoc_classified = Parser().parse_file(open(tlink_file, "r"))
xmldoc_original = Parser().parse_file(open(original_file, "r"))
"""
Verb event should be a dictionary to map between
an event id and some other lemmas generated from the
initial lemma.
"""
verb_events = {}
"""
EVENT tag sample
<EVENT class="OCCURRENCE" eid="e1000028">
"""
for element in xmldoc_classified.get_tags(EVENT):
if element.is_opening_tag():
eid = element.attrs[EID]
event_content = element.next.content
synsets_event = None
if len(wn.synsets(event_content, 'v')) > 0:
synsets_event = wn.synsets(element.next.content,
'v')[0].lemma_names
verb_morphy = wn.morphy(event_content, 'v')
verb_events[eid] = {
MORPHY_LEMMA: verb_morphy,
SYNSET_LEMMA: synsets_event
}
"""
<MAKEINSTANCE eventID="e2" polarity="POS" pos="VERB" eiid="ei2"
tense="PRESENT" aspect="PERFECTIVE">
"""
verb_event_instance = {}
for element in xmldoc_classified.get_tags(INSTANCE):
if element.is_opening_tag():
eiid = element.attrs[EIID]
eid = element.attrs[EVENTID]
if eid in verb_events:
verb_event_instance[eiid] = verb_events[eid]
"""
All TLINKS in the document that are of two events
"""
ee_tlinks = []
for element in xmldoc_classified.get_tags(TLINK):
# keep track of event order here
if element.is_opening_tag():
lid = element.attrs[LID]
if EVENT_INSTANCE_ID in element.attrs:
eiid = element.attrs[EVENT_INSTANCE_ID]
if RELATED_TO_EVENT_INSTANCE in element.attrs:
reiid = element.attrs[RELATED_TO_EVENT_INSTANCE]
if RELTYPE in element.attrs:
if eiid in verb_event_instance and reiid in verb_event_instance:
ee_tlinks.append(
(eiid, reiid, (lid, element.attrs[RELTYPE])))
"""
All TLINKs in the original document between two events
Because excepts the TLINKs parts, original and classified
documents should be identical, so they could use the same
verb_event_instance.
"""
original_ee_tlinks = {}
for element in xmldoc_original.get_tags(TLINK):
# keep track of event order here
if element.is_opening_tag():
lid = element.attrs[LID]
if EVENT_INSTANCE_ID in element.attrs:
eiid = element.attrs[EVENT_INSTANCE_ID]
if RELATED_TO_EVENT_INSTANCE in element.attrs:
reiid = element.attrs[RELATED_TO_EVENT_INSTANCE]
if RELTYPE in element.attrs:
if eiid in verb_event_instance and reiid in verb_event_instance:
original_ee_tlinks[(eiid, reiid)] = (
lid, element.attrs[RELTYPE])
no_of_pair_in_database = 0
no_of_pair = 0
"""
No of pairs of events that are found in
classified files, original files and narrative scheme.
"""
no_of_compare_pairs = 0
"""
No of pairs of events that are found in
classified files, original files and narrative scheme
and that doesn't have matching relation type between
classified and original files
"""
no_of_incompatible_pairs = 0
no_of_verb_events = len(verb_events)
for eiid, reiid, tlink in ee_tlinks:
no_of_pair += 1
"""
Here accessing verb_event_instance given the event instance id
would give the result to be a dictionary of lemmas.
"""
lemma_dict_1 = verb_event_instance[eiid]
lemma_dict_2 = verb_event_instance[reiid]
logging.info(
"---------------------------------------------------------------")
logging.info("---------Classified file---------")
logging.info("Tlink id in classified file is %s" % tlink[0])
relType = tlink[1]
logging.info("Label in classified file is %s" % relType)
if (eiid, reiid) in original_ee_tlinks:
no_of_compare_pairs += 1
original_relation = original_ee_tlinks[(eiid, reiid)][1]
logging.info("---------Original file---------")
logging.info("Tlink id in classified file is %s" %
original_ee_tlinks[(eiid, reiid)][0])
logging.info("Label in classified file is %s" % original_relation)
if relType != original_relation:
no_of_incompatible_pairs += 1
elif (reiid, eiid) in original_ee_tlinks:
no_of_compare_pairs += 1
original_relation = reverse(original_ee_tlinks[(reiid, eiid)][1])
logging.info("---------Original file---------")
logging.info("In the original file, the TLINK is %s" %
original_relation)
logging.info("Tlink in original file %s" %
original_ee_tlinks[(reiid, eiid)][0])
if relType != original_relation:
no_of_incompatible_pairs += 1
else:
continue
logging.info("---------LEMMA---------")
if lemma_dict_1[MORPHY_LEMMA] != None and lemma_dict_2[
MORPHY_LEMMA] != None:
v_1 = lemma_dict_1[MORPHY_LEMMA]
v_2 = lemma_dict_2[MORPHY_LEMMA]
if v_1 == v_2:
continue
try:
result = narrative_checker.check_in_dict(v_1, v_2)
if result != None:
logging.info("%s, %s, %d, %d" %
(v_1, v_2, result[0], result[1]))
except Exception as e:
logging.error(str(e))
logging.info("---------SYNSET---------")
sum_result = [0, 0]
if lemma_dict_1[SYNSET_LEMMA] != None and lemma_dict_2[
SYNSET_LEMMA] != None:
v_1_list = lemma_dict_1[SYNSET_LEMMA]
v_2_list = lemma_dict_2[SYNSET_LEMMA]
for v_1, v_2 in itertools.product(v_1_list, v_2_list):
if v_1 == v_2:
continue
try:
result = narrative_checker.check_in_dict(v_1, v_2)
if result != None:
sum_result[0] += result[0]
sum_result[1] += result[1]
except Exception as e:
logging.error(str(e))
logging.info(
"%s\n %s\n %d, %d" %
(str(v_1_list), str(v_2_list), sum_result[0], sum_result[1]))
no_of_pair_in_database += 1
logging.info('Number of events tlink: %d' % no_of_pair)
logging.info('Number of pairs in database : %d' % no_of_pair_in_database)
logging.info('Percentage of pairs that are found \
in narrative scheme database: %.2f' %
(float(no_of_pair_in_database) / no_of_pair))
logging.info('Number of pairs that are found in database\
and original files as well %d' % no_of_compare_pairs)
logging.info('Number of pairs that are found in database\
and original files and not compatible %d' %
no_of_incompatible_pairs)
logging.info(
'============================================================')
