def test_json_grammar_export(self):
dog = build_acyclic_dog()
terminals = Enumerator()
data = dog.export_graph_json(terminals)
with open('/tmp/json_graph_1.json', 'w') as file:
json.dump(data, file)
dsg = build_dsg()
data = dsg.export_bihypergraph_json(terminals)
with open('/tmp/json_bigraph_1.json', 'w') as file:
json.dump(data, file)
rule_dog = dog_se()
data2 = rule_dog.export_graph_json(terminals)
with open('/tmp/json_nonterminal_graph_1.json', 'w') as file:
json.dump(data2, file)
terminals.print_index()
dsg = build_dsg()
rec_part_strategy = the_recursive_partitioning_factory().get_partitioning('right-branching')[0]
rec_part = rec_part_strategy(dsg)
dcmp = compute_decomposition(dsg, rec_part)
grammar = induce_grammar_from(dsg, rec_part, dcmp, labeling=simple_labeling, terminal_labeling=str)
print(grammar)
data = export_dog_grammar_to_json(grammar, terminals)
with open('/tmp/json_grammar.json', 'w') as file:
json.dump(data, file)
with open('/tmp/json_corpus.json', 'w') as file:
json.dump(export_corpus_to_json([dsg], terminals), file)
def test_json_export(self):
dog = build_acyclic_dog()
terminals = Enumerator()
data = dog.export_graph_json(terminals)
with open('/tmp/json_graph_1.json', 'w') as file:
json.dump(data, file)
dsg = build_dsg()
data = dsg.export_bihypergraph_json(terminals)
with open('/tmp/json_bigraph_1.json', 'w') as file:
json.dump(data, file)
rule_dog = dog_se()
data2 = rule_dog.export_graph_json(terminals)
with open('/tmp/json_nonterminal_graph_1.json', 'w') as file:
json.dump(data2, file)
terminals.print_index()
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 linearize(grammar,
nonterminal_labeling,
terminal_labeling,
file,
delimiter='::',
nonterminal_encoder=None):
"""
:type grammar: LCFRS
:param nonterminal_labeling:
:param terminal_labeling:
:param file: file handle to write to
:type delimiter: str
:param delimiter: string used to join terminal symbol with edge label symbol
:type nonterminal_encoder: Enumerator
:param nonterminal_encoder: mapping that assigns unique non-negative integer to each nonterminal
"""
print("Nonterminal Labeling: ", nonterminal_labeling, file=file)
print("Terminal Labeling: ", terminal_labeling, file=file)
print(file=file)
terminals = Enumerator(first_index=1)
if nonterminal_encoder is None:
nonterminals = Enumerator()
else:
nonterminals = nonterminal_encoder
num_inherited_args = {}
num_synthesized_args = {}
for rule in grammar.rules():
rid = 'r%i' % (rule.get_idx() + 1)
print(rid,
'RTG ',
nonterminals.object_index(rule.lhs().nont()),
'->',
file=file,
end=" ")
print(list(
map(lambda nont: nonterminals.object_index(nont), rule.rhs())),
';',
file=file)
print(rid, 'WEIGHT', rule.weight(), ';', file=file)
sync_index = {}
inh_args = defaultdict(lambda: 0)
lhs_var_counter = CountLHSVars()
synthesized_attributes = 0
dcp_ordered = sorted(rule.dcp(),
key=lambda x: (x.lhs().mem(), x.lhs().arg()))
for dcp in dcp_ordered:
if dcp.lhs().mem() != -1:
inh_args[dcp.lhs().mem()] += 1
else:
synthesized_attributes += 1
lhs_var_counter.evaluate_list(dcp.rhs())
num_inherited_args[nonterminals.object_index(
rule.lhs().nont())] = inh_args[-1] = lhs_var_counter.get_number()
num_synthesized_args[nonterminals.object_index(
rule.lhs().nont())] = synthesized_attributes
for dcp in dcp_ordered:
printer = DcpPrinter(terminals.object_index,
rule,
sync_index,
inh_args,
delimiter=delimiter)
printer.evaluate_list(dcp.rhs())
var = dcp.lhs()
if var.mem() == -1:
var_string = 's<0,%i>' % (var.arg() + 1 - inh_args[-1])
else:
var_string = 's<%i,%i>' % (var.mem() + 1, var.arg() + 1)
print('%s sDCP %s == %s ;' % (rid, var_string, printer.string),
file=file)
s = 0
for j, arg in enumerate(rule.lhs().args()):
print(rid, 'LCFRS s<0,%i> == [' % (j + 1), end=' ', file=file)
first = True
for a in arg:
if not first:
print(",", end=' ', file=file)
if isinstance(a, LCFRS_var):
print("x<%i,%i>" % (a.mem + 1, a.arg + 1),
end=' ',
file=file)
pass
else:
if s in sync_index:
print(str(terminals.object_index(a)) +
'^{%i}' % sync_index[s],
end=' ',
file=file)
else:
print(str(terminals.object_index(a)),
end=' ',
file=file)
s += 1
first = False
print('] ;', file=file)
print(file=file)
print("Terminals: ", file=file)
terminals.print_index(to_file=file)
print(file=file)
print("Nonterminal ID, nonterminal name, fanout, #inh, #synth: ",
file=file)
max_fanout, max_inh, max_syn, max_args, fanouts, inherits, synths, args \
= print_index_and_stats(nonterminals, grammar, num_inherited_args, num_synthesized_args, file=file)
print(file=file)
print("max fanout:", max_fanout, file=file)
print("max inh:", max_inh, file=file)
print("max synth:", max_syn, file=file)
print("max args:", max_args, file=file)
print(file=file)
for s, d, m in [('fanout', fanouts, max_fanout),
('inh', inherits, max_inh), ('syn', synths, max_syn),
('args', args, max_args)]:
for i in range(m + 1):
print('# the number of nonterminals with %s = %i is %i' %
(s, i, d[i]),
file=file)
print(file=file)
print(file=file)
print("Initial nonterminal: ",
nonterminals.object_index(grammar.start()),
file=file)
print(file=file)
return nonterminals, terminals
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