def cut_sent(self, text: str, sid=None) -> List[Sentence]:
last_cut = 0
sentences = []
for i in range(0, len(text) - 1):
if text[i] in self._eos:
sentences.append(Sentence([TEXT(text[last_cut:i + 1])]))
last_cut = i + 1
if last_cut < len(text) - 1:
sentences.append(Sentence([TEXT(text[last_cut:])]))
return sentences
def parse(self, para):
edus = []
for edu in para.edus():
edu_copy = EDU([TEXT(edu.text)])
setattr(edu_copy, "words", edu.words)
setattr(edu_copy, "tags", edu.tags)
edus.append(edu_copy)
return self.parser.parse(edus)
def cut_edu(self, sent: Sentence) -> List[EDU]:
if not hasattr(sent, "parse"):
print(sent.text)
parse = self.parser.parse(sent.text)
else:
parse = getattr(sent, "parse")
parse = ParentedTree.fromstring(parse.pformat())
children = list(
parse.subtrees(
lambda t: t.height() == 2 and t.label() != '-NONE-'))
edus = []
last_edu_words = []
last_edu_tags = []
offset = 0
for child in children:
if child[0] == '-LRB-':
child[0] = '('
if child[0] == '-RRB-':
child[0] = ')'
last_edu_words.append(child[0])
last_edu_tags.append(child.label())
if child[0] in self._eos or (child[0] in self.candidate and
self.model.predict(offset, parse)):
text = "".join(last_edu_words)
edu = EDU([TEXT(text)])
setattr(edu, "words", last_edu_words)
setattr(edu, "tags", last_edu_tags)
edus.append(edu)
last_edu_words = []
last_edu_tags = []
offset += len(child[0])
if last_edu_words:
text = "".join(last_edu_words)
edu = EDU([TEXT(text)])
setattr(edu, "words", last_edu_words)
setattr(edu, "tags", last_edu_tags)
edus.append(edu)
return edus
def parse_and_eval(dataset, model):
model.eval()
parser = PartitionPtrParser(model)
golds = list(filter(lambda d: d.root_relation(), chain(*dataset)))
num_instances = len(golds)
strips = []
for paragraph in golds:
edus = []
for edu in paragraph.edus():
edu_copy = EDU([TEXT(edu.text)])
setattr(edu_copy, "words", edu.words)
setattr(edu_copy, "tags", edu.tags)
edus.append(edu_copy)
strips.append(edus)
parses = []
for edus in strips:
parse = parser.parse(edus)
parses.append(parse)
return num_instances, parse_eval(parses, golds)
def main():
logging.basicConfig(level=logging.INFO)
with open("data/models/treebuilder.partptr.model", "rb") as model_fd:
model = torch.load(model_fd, map_location="cpu")
model.eval()
model.use_gpu = False
parser = PartitionPtrParser(model)
cdtb = CDTB("data/CDTB",
"TRAIN",
"VALIDATE",
"TEST",
ctb_dir="data/CTB",
preprocess=True,
cache_dir="data/cache")
golds = list(filter(lambda d: d.root_relation(), chain(*cdtb.test)))
strips = []
for paragraph in golds:
edus = []
for edu in paragraph.edus():
edu_copy = EDU([TEXT(edu.text)])
setattr(edu_copy, "words", edu.words)
setattr(edu_copy, "tags", edu.tags)
edus.append(edu_copy)
strips.append(edus)
parses = []
parse_sessions = []
for edus in strips:
parse, session = parser.parse(edus, ret_session=True)
parses.append(parse)
parse_sessions.append(session)
# macro cdtb scores
cdtb_macro_scores = eval.parse_eval(parses, golds, average="macro")
logging.info("CDTB macro (strict) scores:")
logging.info(eval.gen_parse_report(*cdtb_macro_scores))
# micro cdtb scores
cdtb_micro_scores = eval.parse_eval(parses, golds, average="micro")
logging.info("CDTB micro (strict) scores:")
logging.info(eval.gen_parse_report(*cdtb_micro_scores))
# micro rst scores
rst_scores = eval.rst_parse_eval(parses, golds)
logging.info("RST styled scores:")
logging.info(eval.gen_parse_report(*rst_scores))
# nuclear scores
nuclear_scores = eval.nuclear_eval(parses, golds)
logging.info("nuclear scores:")
logging.info(eval.gen_category_report(nuclear_scores))
# relation scores
ctype_scores, ftype_scores = eval.relation_eval(parses, golds)
logging.info("coarse relation scores:")
logging.info(eval.gen_category_report(ctype_scores))
logging.info("fine relation scores:")
logging.info(eval.gen_category_report(ftype_scores))
# draw gold and parse tree along with decision hotmap
for gold, parse, session in zip(golds, parses, parse_sessions):
gold.draw()
session.draw_decision_hotmap()
parse.draw()