def test_something(self):
grammar, r1, r2 = self.build_grammar()
nont_map = Enumerator()
grammarInfo = PyGrammarInfo(grammar, nont_map)
def w(x):
return "S", x
rtg = RTG(w(3))
rtg.construct_and_add_rule(w(3), r1, [w(1), w(2)])
rtg.construct_and_add_rule(w(3), r1, [w(2), w(1)])
rtg.construct_and_add_rule(w(2), r1, [w(1), w(1)])
rtg.construct_and_add_rule(w(1), r2, [])
rtg2 = RTG(("A", 3))
rtg3 = RTG(w(3))
rtg3.construct_and_add_rule(w(3), r1, [w(1), w(2)])
rtg3.construct_and_add_rule(w(3), r1, [w(2), w(1)])
rtg3.construct_and_add_rule(w(2), r2, [w(1), w(1)])
rtg3.construct_and_add_rule(w(1), r2, [])
traces = PyDerivationManager(grammar, nont_map)
traces.convert_rtgs_to_hypergraphs([rtg, rtg2, rtg3])
self.assertTrue(
traces.is_consistent_with_grammar(grammarInfo, traceId=0))
self.assertFalse(
traces.is_consistent_with_grammar(grammarInfo, traceId=1))
self.assertFalse(
traces.is_consistent_with_grammar(grammarInfo, traceId=2))
def test_negra_to_dag_parsing(self):
names = list(map(str, [26954]))
fd_, primary_file = tempfile.mkstemp(suffix='.export')
with open(primary_file, mode='w') as pf:
for s in names:
dsg = tp.sentence_names_to_deep_syntax_graphs(
["s" + s],
"res/tiger/tiger_s%s.xml" % s,
hold=False,
ignore_puntcuation=False)[0]
dsg.set_label(dsg.label[1:])
lines = np.serialize_hybrid_dag_to_negra(
[dsg], 0, 500, use_sentence_names=True)
print(''.join(lines), file=pf)
_, binarized_file = tempfile.mkstemp(suffix='.export')
subprocess.call([
"discodop", "treetransforms", "--binarize", "-v", "1", "-h", "1",
primary_file, binarized_file
])
print(primary_file)
print(binarized_file)
corpus = np.sentence_names_to_hybridtrees(names,
primary_file,
secedge=True)
corpus2 = np.sentence_names_to_hybridtrees(names,
binarized_file,
secedge=True)
dag = corpus[0]
print(dag)
assert isinstance(dag, HybridDag)
self.assertEqual(8, len(dag.token_yield()))
for token in dag.token_yield():
print(token.form() + '/' + token.pos(), end=' ')
print()
dag_bin = corpus2[0]
print(dag_bin)
for token in dag_bin.token_yield():
print(token.form() + '/' + token.pos(), end=' ')
print()
self.assertEqual(8, len(dag_bin.token_yield()))
for node, token in zip(
dag_bin.nodes(),
list(map(str, map(dag_bin.node_token, dag_bin.nodes())))):
print(node, token)
print()
print(top(dag_bin, {'500', '101', '102'}))
self.assertSetEqual({'101', '500'}, top(dag_bin,
{'500', '101', '102'}))
print(bottom(dag_bin, {'500', '101', '102'}))
self.assertSetEqual({'502'}, bottom(dag_bin, {'500', '101', '102'}))
nont_labeling = BasicNonterminalLabeling()
term_labeling = FormTerminals() # PosTerminals()
grammar = direct_extract_lcfrs_from_prebinarized_corpus(
dag_bin, term_labeling, nont_labeling)
# print(grammar)
for rule in grammar.rules():
print(rule.get_idx(), rule)
print("Testing LCFRS parsing and DCP evaluation".center(80, '='))
parser = LCFRS_parser(grammar)
parser_input = term_labeling.prepare_parser_input(
dag_bin.token_yield())
print(parser_input)
parser.set_input(parser_input)
parser.parse()
self.assertTrue(parser.recognized())
der = parser.best_derivation_tree()
print(der)
dcp_term = DCP_evaluator(der).getEvaluation()
print(dcp_term[0])
dag_eval = HybridDag(dag_bin.sent_label())
dcp_to_hybriddag(dag_eval,
dcp_term,
copy.deepcopy(dag_bin.token_yield()),
False,
construct_token=construct_constituent_token)
print(dag_eval)
for node in dag_eval.nodes():
token = dag_eval.node_token(node)
if token.type() == "CONSTITUENT-CATEGORY":
label = token.category()
elif token.type() == "CONSTITUENT-TERMINAL":
label = token.form(), token.pos()
print(node, label, dag_eval.children(node),
dag_eval.sec_children(node), dag_eval.sec_parents(node))
lines = np.serialize_hybridtrees_to_negra([dag_eval],
1,
500,
use_sentence_names=True)
for line in lines:
print(line, end='')
print()
with open(primary_file) as pcf:
for line in pcf:
print(line, end='')
print('Testing reduct computation with Schick parser'.center(80, '='))
grammar_path = '/tmp/lcfrs_dcp_grammar.gr'
derivation_manager = PyDerivationManager(grammar)
with open(grammar_path, 'w') as grammar_file:
nonterminal_enc, terminal_enc = linearize(
grammar,
nont_labeling,
term_labeling,
grammar_file,
delimiter=' : ',
nonterminal_encoder=derivation_manager.get_nonterminal_map())
print(np.negra_to_json(dag, terminal_enc, term_labeling))
json_data = np.export_corpus_to_json([dag], terminal_enc,
term_labeling)
corpus_path = '/tmp/json_dags.json'
with open(corpus_path, 'w') as data_file:
json.dump(json_data, data_file)
reduct_dir = '/tmp/schick_parser_reducts'
if os.path.isdir(reduct_dir):
shutil.rmtree(reduct_dir)
os.makedirs(reduct_dir)
p = subprocess.Popen([
' '.join([
"java", "-jar",
os.path.join("util",
SCHICK_PARSER_JAR), 'reduct', '-g', grammar_path,
'-t', corpus_path, "--input-format", "json", "-o", reduct_dir
])
],
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
print("stdout", p.stdout.name)
while True:
nextline = p.stdout.readline()
if nextline == b'' and p.poll() is not None:
break
print(nextline.decode('unicode_escape'), end='')
# sys.stdout.write(nextline)
# sys.stdout.flush()
p.wait()
p.stdout.close()
self.assertEqual(0, p.returncode)
rtgs = []
def decode_nonterminals(s):
return derivation_manager.get_nonterminal_map().index_object(
int(s))
for i in range(1, len(corpus) + 1):
rtgs.append(
read_rtg(os.path.join(reduct_dir,
str(i) + '.gra'),
symbol_offset=-1,
rule_prefix='r',
process_nonterminal=decode_nonterminals))
print("Reduct RTG")
for rule in rtgs[0].rules:
print(rule.lhs, "->", rule.symbol, rule.rhs)
derivation_manager.get_nonterminal_map().print_index()
derivation_manager.convert_rtgs_to_hypergraphs(rtgs)
derivation_manager.serialize(
bytes('/tmp/reduct_manager.trace', encoding='utf8'))
derivations = [
LCFRSDerivationWrapper(der)
for der in derivation_manager.enumerate_derivations(0, grammar)
]
self.assertGreaterEqual(len(derivations), 1)
if len(derivations) >= 1:
print("Sentence", i)
for der in derivations:
print(der)
self.assertTrue(
der.check_integrity_recursive(der.root_id(),
grammar.start()))
def test_json_corpus_grammar_export(self):
start = 1
stop = 50
# path = "res/tiger/tiger_release_aug07.corrected.16012013.utf8.xml"
path = "res/tiger/tiger_8000.xml"
exclude = []
dsgs = sentence_names_to_deep_syntax_graphs(
['s' + str(i) for i in range(start, stop + 1) if i not in exclude]
, path
, hold=False)
rec_part_strategy = the_recursive_partitioning_factory().get_partitioning('cfg')[0]
def label_edge(edge):
if isinstance(edge.label, ConstituentTerminal):
return edge.label.pos()
else:
return edge.label
nonterminal_labeling = lambda nodes, dsg: simple_labeling(nodes, dsg, label_edge)
term_labeling_token = PosTerminals()
def term_labeling(token):
if isinstance(token, ConstituentTerminal):
return term_labeling_token.token_label(token)
else:
return token
grammar = induction_on_a_corpus(dsgs, rec_part_strategy, nonterminal_labeling, term_labeling)
grammar.make_proper()
terminals = Enumerator()
data = export_dog_grammar_to_json(grammar, terminals)
grammar_path = '/tmp/json_grammar.json'
with open(grammar_path, 'w') as file:
json.dump(data, file)
corpus_path = '/tmp/json_corpus.json'
with open(corpus_path, 'w') as file:
json.dump(export_corpus_to_json(dsgs, terminals, terminal_labeling=term_labeling), file)
with open('/tmp/enumerator.enum', 'w') as file:
terminals.print_index(file)
reduct_dir = '/tmp/reduct_grammars'
if os.path.isdir(reduct_dir):
shutil.rmtree(reduct_dir)
os.makedirs(reduct_dir)
p = subprocess.Popen([' '.join(
["java", "-jar", os.path.join("util", SCHICK_PARSER_JAR), 'dog-reduct', '-g', grammar_path, '-t',
corpus_path, "-o", reduct_dir])], shell=True, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
print("stdout", p.stdout.name)
while True:
nextline = p.stdout.readline()
if nextline == b'' and p.poll() is not None:
break
print(nextline.decode('unicode_escape'), end='')
# sys.stdout.write(nextline)
# sys.stdout.flush()
p.wait()
p.stdout.close()
self.assertEqual(0, p.returncode)
rtgs = []
for i in range(1, len(dsgs) + 1):
rtgs.append(read_rtg('/tmp/reduct_grammars/' + str(i) + '.gra'))
derivation_manager = PyDerivationManager(grammar)
derivation_manager.convert_rtgs_to_hypergraphs(rtgs)
derivation_manager.serialize(bytes('/tmp/reduct_manager.trace', encoding='utf8'))
f = lambda token: token.pos() if isinstance(token, ConstituentTerminal) else token
for i, (rtg, dsg) in enumerate(zip(rtgs, dsgs)):
derivations = [LCFRSDerivationWrapper(der) for der in derivation_manager.enumerate_derivations(i, grammar)]
self.assertGreaterEqual(len(derivations), 1)
if len(derivations) > 1:
print("Sentence", i)
for der in derivations:
print(der)
for der in derivations:
dog, sync = dog_evaluation(der)
dsg2 = DeepSyntaxGraph(der.compute_yield(), dog, sync)
dsg.dog.project_labels(f)
dsg.sentence = list(map(f, dsg.sentence))
self.assertEqual(dsg.sentence, dsg2.sentence)
morphs = dsg.dog.compute_isomorphism(dsg2.dog)
self.assertFalse(morphs is None)
self.assertListEqual([[morphs[0].get(node, node) for node in syncs]
for syncs in dsg.synchronization], dsg2.synchronization)
pass
def run_experiment(rec_part_strategy,
nonterminal_labeling,
exp,
reorder_children,
binarize=True):
start = 1
stop = 7000
test_start = 7001
test_stop = 7200
# path = "res/tiger/tiger_release_aug07.corrected.16012013.utf8.xml"
corpus_path = "res/tiger/tiger_8000.xml"
exclude = []
train_dsgs = sentence_names_to_deep_syntax_graphs(
['s' + str(i) for i in range(start, stop + 1) if i not in exclude],
corpus_path,
hold=False,
reorder_children=reorder_children)
test_dsgs = sentence_names_to_deep_syntax_graphs(
[
's' + str(i)
for i in range(test_start, test_stop + 1) if i not in exclude
],
corpus_path,
hold=False,
reorder_children=reorder_children)
# Grammar induction
term_labeling_token = PosTerminals()
def term_labeling(token):
if isinstance(token, ConstituentTerminal):
return term_labeling_token.token_label(token)
else:
return token
if binarize:
def modify_token(token):
if isinstance(token, ConstituentCategory):
token_new = deepcopy(token)
token_new.set_category(token.category() + '-BAR')
return token_new
elif isinstance(token, str):
return token + '-BAR'
else:
assert False
train_dsgs = [
dsg.binarize(bin_modifier=modify_token) for dsg in train_dsgs
]
def is_bin(token):
if isinstance(token, ConstituentCategory):
if token.category().endswith('-BAR'):
return True
elif isinstance(token, str):
if token.endswith('-BAR'):
return True
return False
def debinarize(dsg):
return dsg.debinarize(is_bin=is_bin)
else:
debinarize = id
grammar = induction_on_a_corpus(train_dsgs, rec_part_strategy,
nonterminal_labeling, term_labeling)
grammar.make_proper()
print("Nonterminals", len(grammar.nonts()), "Rules", len(grammar.rules()))
parser = GFParser_k_best(grammar, k=500)
return do_parsing(parser,
test_dsgs,
term_labeling_token,
oracle=True,
debinarize=debinarize)
# Compute reducts, i.e., intersect grammar with each training dsg
basedir = path.join('/tmp/dog_experiments', 'exp' + str(exp))
reduct_dir = path.join(basedir, 'reduct_grammars')
terminal_map = Enumerator()
if not os.path.isdir(basedir):
os.makedirs(basedir)
data = export_dog_grammar_to_json(grammar, terminal_map)
grammar_path = path.join(basedir, 'grammar.json')
with open(grammar_path, 'w') as file:
json.dump(data, file)
corpus_path = path.join(basedir, 'corpus.json')
with open(corpus_path, 'w') as file:
json.dump(
export_corpus_to_json(train_dsgs,
terminal_map,
terminal_labeling=term_labeling), file)
with open(path.join(basedir, 'enumerator.enum'), 'w') as file:
terminal_map.print_index(file)
if os.path.isdir(reduct_dir):
shutil.rmtree(reduct_dir)
os.makedirs(reduct_dir)
p = subprocess.Popen([
' '.join([
"java", "-jar",
os.path.join("util", SCHICK_PARSER_JAR), 'dog-reduct', '-g',
grammar_path, '-t', corpus_path, "-o", reduct_dir
])
],
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
while True:
nextline = p.stdout.readline()
if nextline == '' and p.poll() is not None:
break
sys.stdout.write(nextline)
sys.stdout.flush()
p.wait()
p.stdout.close()
rtgs = []
for i in range(1, len(train_dsgs) + 1):
rtgs.append(read_rtg(path.join(reduct_dir, str(i) + '.gra')))
derivation_manager = PyDerivationManager(grammar)
derivation_manager.convert_rtgs_to_hypergraphs(rtgs)
derivation_manager.serialize(path.join(basedir, 'reduct_manager.trace'))
# Training
## prepare EM training
em_epochs = 20
seed = 0
smoothing_factor = 0.01
split_randomization = 0.01
sm_cycles = 2
merge_percentage = 50.0
grammarInfo = PyGrammarInfo(grammar,
derivation_manager.get_nonterminal_map())
storageManager = PyStorageManager()
em_builder = PySplitMergeTrainerBuilder(derivation_manager, grammarInfo)
em_builder.set_em_epochs(em_epochs)
em_builder.set_simple_expector(threads=THREADS)
emTrainer = em_builder.build()
# randomize initial weights and do em training
la_no_splits = build_PyLatentAnnotation_initial(grammar, grammarInfo,
storageManager)
la_no_splits.add_random_noise(seed=seed)
emTrainer.em_train(la_no_splits)
la_no_splits.project_weights(grammar, grammarInfo)
do_parsing(CFGParser(grammar), test_dsgs, term_labeling_token)
return
## prepare SM training
builder = PySplitMergeTrainerBuilder(derivation_manager, grammarInfo)
builder.set_em_epochs(em_epochs)
builder.set_split_randomization(1.0, seed + 1)
builder.set_simple_expector(threads=THREADS)
builder.set_smoothing_factor(smoothingFactor=smoothing_factor)
builder.set_split_randomization(percent=split_randomization)
# builder.set_scc_merger(-0.2)
builder.set_percent_merger(merge_percentage)
splitMergeTrainer = builder.build()
# splitMergeTrainer.setMaxDrops(validationDropIterations, mode="smoothing")
splitMergeTrainer.setEMepochs(em_epochs, mode="smoothing")
# set initial latent annotation
latentAnnotation = [la_no_splits]
# carry out split/merge training and do parsing
parsing_method = "filter-ctf"
# parsing_method = "single-best-annotation"
k_best = 50
for i in range(1, sm_cycles + 1):
splitMergeTrainer.reset_random_seed(seed + i + 1)
latentAnnotation.append(
splitMergeTrainer.split_merge_cycle(latentAnnotation[-1]))
print("Cycle: ", i)
if parsing_method == "single-best-annotation":
smGrammar = latentAnnotation[i].build_sm_grammar(
grammar, grammarInfo, rule_pruning=0.0001, rule_smoothing=0.1)
print("Rules in smoothed grammar: ", len(smGrammar.rules()))
parser = GFParser(smGrammar)
elif parsing_method == "filter-ctf":
latentAnnotation[-1].project_weights(grammar, grammarInfo)
parser = Coarse_to_fine_parser(
grammar,
latentAnnotation[-1],
grammarInfo,
derivation_manager.get_nonterminal_map(),
base_parser_type=GFParser_k_best,
k=k_best)
else:
raise (Exception())
do_parsing(parser, test_dsgs, term_labeling_token)
del parser