def latent_viterbi_derivation(self, debug=False):
manager = PyDerivationManager(self.grammar, self.nontMap)
manager.convert_chart_to_hypergraph(self.chart, self.disco_grammar, debug=False)
if debug:
manager.serialize(b'/tmp/my_debug_hypergraph.hg')
if isinstance(self.la, list):
la = self.la[0]
else:
la = self.la
vit_der = manager.latent_viterbi_derivation(0, la, self.grammar, debug=debug)
# if len(self.input) < 15 and not debug:
# for weight, der in self.k_best_derivation_trees():
# if der != vit_der:
# print(weight, der, vit_der)
# vit_der2 = self.latent_viterbi_derivation(debug=True)
# print("vit2", vit_der2)
# if vit_der2 != vit_der:
# print("first and second viterbi derivation differ")
# if vit_der2 == der:
# print("second viterbi derivation = 1-best-disco-dop derivation")
# print("##############################", flush=True)
# break
# # raise Exception("too much to read")
if vit_der is not None:
vit_der = LCFRSDerivationWrapper(vit_der)
return vit_der
def main():
# induce grammar from a corpus
trees = parse_conll_corpus(train, False, limit_train)
nonterminal_labelling = the_labeling_factory(
).create_simple_labeling_strategy("childtop", "deprel")
term_labelling = the_terminal_labeling_factory().get_strategy('pos')
start = 'START'
recursive_partitioning = [cfg]
_, grammar = induce_grammar(trees, nonterminal_labelling,
term_labelling.token_label,
recursive_partitioning, start)
# compute some derivations
derivations = obtain_derivations(grammar, term_labelling)
# create derivation manager and add derivations
manager = PyDerivationManager(grammar)
manager.convert_derivations_to_hypergraphs(derivations)
manager.serialize(b"/tmp/derivations.txt")
# build and configure split/merge trainer and supplementary objects
rule_to_nonterminals = []
for i in range(0, len(grammar.rule_index())):
rule = grammar.rule_index(i)
nonts = [
manager.get_nonterminal_map().object_index(rule.lhs().nont())
] + [
manager.get_nonterminal_map().object_index(nont)
for nont in rule.rhs()
]
rule_to_nonterminals.append(nonts)
grammarInfo = PyGrammarInfo(grammar, manager.get_nonterminal_map())
storageManager = PyStorageManager()
builder = PySplitMergeTrainerBuilder(manager, grammarInfo)
builder.set_em_epochs(20)
builder.set_percent_merger(60.0)
splitMergeTrainer = builder.build()
latentAnnotation = [
build_PyLatentAnnotation_initial(grammar, grammarInfo, storageManager)
]
for i in range(max_cycles + 1):
latentAnnotation.append(
splitMergeTrainer.split_merge_cycle(latentAnnotation[-1]))
# pickle.dump(map(lambda la: la.serialize(), latentAnnotation), open(sm_info_path, 'wb'))
smGrammar = build_sm_grammar(latentAnnotation[i],
grammar,
grammarInfo,
rule_pruning=0.0001,
rule_smoothing=0.01)
print("Cycle: ", i, "Rules: ", len(smGrammar.rules()))
if parsing:
parser = GFParser(smGrammar)
trees = parse_conll_corpus(test, False, limit_test)
for tree in trees:
parser.set_input(
term_labelling.prepare_parser_input(tree.token_yield()))
parser.parse()
if parser.recognized():
print(
derivation_to_hybrid_tree(
parser.best_derivation_tree(),
[token.pos() for token in tree.token_yield()],
[token.form() for token in tree.token_yield()],
construct_constituent_token))
def test_individual_parsing_stages(self):
grammar = self.build_grammar()
for r in transform_grammar(grammar):
pprint(r)
rule_list = list(transform_grammar(grammar))
pprint(rule_list)
disco_grammar = Grammar(rule_list, start=grammar.start())
print(disco_grammar)
inp = ["a"] * 3
estimates = 'SXlrgaps', getestimates(disco_grammar, 40, grammar.start())
print(type(estimates))
chart, msg = parse(inp, disco_grammar, estimates=estimates)
print(chart)
print(msg)
chart.filter()
print("filtered chart")
print(disco_grammar.nonterminals)
print(type(disco_grammar.nonterminals))
print(chart)
# print(help(chart))
root = chart.root()
print("root", root, type(root))
print(chart.indices(root))
print(chart.itemstr(root))
print(chart.stats())
print("root label", chart.label(root))
print(root, chart.itemid1(chart.label(root), chart.indices(root)))
for i in range(1, chart.numitems() + 1):
print(i, chart.label(i), chart.indices(i), chart.numedges(i))
if True or len(chart.indices(i)) > 1:
for edge_num in range(chart.numedges(i)):
edge = chart.getEdgeForItem(i, edge_num)
if isinstance(edge, tuple):
print("\t", disco_grammar.nonterminalstr(chart.label(i)) + "[" + str(i) + "]", "->", ' '.join([disco_grammar.nonterminalstr(chart.label(j)) + "[" + str(j) + "]" for j in [edge[1], edge[2]] if j != 0]))
else:
print("\t", disco_grammar.nonterminalstr(chart.label(i)) + "[" + str(i) + "]", "->", inp[edge])
print(chart.getEdgeForItem(root, 0))
# print(lazykbest(chart, 5))
manager = PyDerivationManager(grammar)
manager.convert_chart_to_hypergraph(chart, disco_grammar, debug=True)
file = tempfile.mktemp()
print(file)
manager.serialize(bytes(file, encoding="utf-8"))
gi = PyGrammarInfo(grammar, manager.get_nonterminal_map())
sm = PyStorageManager()
la = build_PyLatentAnnotation_initial(grammar, gi, sm)
vec = py_edge_weight_projection(la, manager, variational=True, debug=True, log_mode=False)
print(vec)
self.assertEqual([1.0, 1.0, 1.0, 0.5, 0.5, 0.5, 0.5, 0.25, 0.25, 0.25, 0.25, 1.0], vec)
vec = py_edge_weight_projection(la, manager, variational=False, debug=True, log_mode=False)
print(vec)
self.assertEqual([1.0, 1.0, 1.0, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 0.25, 1.0], vec)
der = manager.viterbi_derivation(0, vec, grammar)
print(der)
# print(disco_grammar.rulenos)
# print(disco_grammar.numrules)
# print(disco_grammar.lexicalbylhs)
# print(disco_grammar.lexicalbyword)
# print(disco_grammar.lexicalbynum)
# print(disco_grammar.origrules, type(disco_grammar.origrules))
# print(disco_grammar.numbinary)
# print(disco_grammar.numunary)
# print(disco_grammar.toid)
# print(disco_grammar.tolabel)
# print(disco_grammar.bitpar)
# striplabelre = re.compile(r'-\d+$')
# msg = disco_grammar.getmapping(None, None)
# disco_grammar.getrulemapping(disco_grammar, striplabelre)
# mapping = disco_grammar.rulemapping
# print(mapping)
# for idx, group in enumerate(mapping):
# print("Index", idx)
# for elem in group:
# print(grammar.rule_index(elem))
# for _, item in zip(range(20), chart.parseforest):
# edge = chart.parseforest[item]
# print(item, item.binrepr(), item.__repr__(), item.lexidx())
# print(type(edge))
for _ in range(5):
vec2 = py_edge_weight_projection(la, manager, debug=True, log_mode=True)
print(vec2)
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
