def do_em_training(self):
em_builder = PySplitMergeTrainerBuilder(
self.organizer.training_reducts, self.organizer.grammarInfo)
em_builder.set_em_epochs(self.organizer.em_epochs)
em_builder.set_simple_expector(threads=self.organizer.threads)
em_builder.set_scc_merger(self.organizer.merge_threshold)
em_builder.set_scc_merge_threshold_function(
self.organizer.merge_interpolation_factor)
self.organizer.emTrainer = emTrainer = em_builder.build()
initial_la = self.create_initial_la()
emTrainer.em_train(initial_la)
try:
initial_la.project_weights(self.base_grammar,
self.organizer.grammarInfo)
except Exception as exc:
nont_idx = exc.args[0]
splits, root_weights, rule_weights = initial_la.serialize()
nont = self.organizer.nonterminal_map.index_object(nont_idx)
print(nont, nont_idx, splits[nont_idx], file=self.logger)
for rule in self.base_grammar.lhs_nont_to_rules(nont):
print(rule, rule_weights[rule.get_idx()], file=self.logger)
raise
self.organizer.latent_annotations[0] = initial_la
self.organizer.last_sm_cycle = 0
self.save_current_la()
def prepare_split_merge_trainer(self):
# prepare SM training
builder = PySplitMergeTrainerBuilder(self.organizer.training_reducts,
self.organizer.grammarInfo)
builder.set_em_epochs(self.organizer.em_epochs_sm)
builder.set_simple_expector(threads=self.organizer.threads)
if self.organizer.validator_type == "SCORE":
builder.set_score_validator(
self.organizer.validator,
self.organizer.validationDropIterations)
elif self.organizer.validator_type == "SIMPLE":
builder.set_simple_validator(
self.organizer.validation_reducts,
self.organizer.validationDropIterations)
builder.set_smoothing_factor(
smoothingFactor=self.organizer.smoothing_factor,
smoothingFactorUnary=self.organizer.smoothing_factor_unary)
builder.set_split_randomization(
percent=self.organizer.split_randomization,
seed=self.organizer.seed + 1)
# set merger
if self.organizer.merge_type == "SCC":
builder.set_scc_merger(self.organizer.merge_threshold)
elif self.organizer.merge_type == "THRESHOLD":
builder.set_threshold_merger(self.organizer.merge_threshold)
else:
builder.set_percent_merger(self.organizer.merge_percentage)
self.custom_sm_options(builder)
self.organizer.splitMergeTrainer = builder.build()
if self.organizer.validator_type in ["SCORE", "SIMPLE"]:
self.organizer.splitMergeTrainer.setMaxDrops(
self.organizer.validationDropIterations, mode="smoothing")
self.organizer.splitMergeTrainer.setMinEpochs(
self.organizer.min_epochs)
self.organizer.splitMergeTrainer.setMinEpochs(
self.organizer.min_epochs_smoothing, mode="smoothing")
self.organizer.splitMergeTrainer.setIgnoreFailures(
self.organizer.ignore_failures_smoothing, mode="smoothing")
self.organizer.splitMergeTrainer.setEMepochs(
self.organizer.em_epochs_sm, mode="smoothing")
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 main():
# # induce or load grammar
# if not os.path.isfile(grammar_path):
# grammar = LCFRS('START')
# for tree in train_corpus:
# if not tree.complete() or tree.empty_fringe():
# continue
# part = recursive_partitioning(tree)
# tree_grammar = fringe_extract_lcfrs(tree, part, naming='child', term_labeling=terminal_labeling)
# grammar.add_gram(tree_grammar)
# grammar.make_proper()
# pickle.dump(grammar, open(grammar_path, 'wb'))
# else:
# grammar = pickle.load(open(grammar_path, 'rb'))
grammar = LCFRS('START')
for tree in train_corpus:
if not tree.complete() or tree.empty_fringe():
continue
part = recursive_partitioning(tree)
tree_grammar = fringe_extract_lcfrs(tree,
part,
naming='child',
term_labeling=terminal_labeling)
grammar.add_gram(tree_grammar)
grammar.make_proper()
# # compute or load reducts
# if not os.path.isfile(reduct_path):
# traceTrain = compute_reducts(grammar, train_corpus, terminal_labeling)
# traceTrain.serialize(reduct_path)
# else:
# traceTrain = PySDCPTraceManager(grammar, terminal_labeling)
# traceTrain.load_traces_from_file(reduct_path)
traceTrain = compute_reducts(grammar, train_corpus, terminal_labeling)
traceValidationGenetic = compute_reducts(grammar,
validation_genetic_corpus,
terminal_labeling)
traceValidation = compute_reducts(grammar, validation_corpus,
terminal_labeling)
# prepare EM training
grammarInfo = PyGrammarInfo(grammar, traceTrain.get_nonterminal_map())
if not grammarInfo.check_for_consistency():
print("[Genetic] GrammarInfo is not consistent!")
storageManager = PyStorageManager()
em_builder = PySplitMergeTrainerBuilder(traceTrain, 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)
# emTrainerOld = PyEMTrainer(traceTrain)
# emTrainerOld.em_training(grammar, 30, "rfe", tie_breaking=True)
# compute parses for validation set
baseline_parser = GFParser_k_best(grammar, k=k_best)
validator = build_score_validator(grammar, grammarInfo,
traceTrain.get_nonterminal_map(),
storageManager, terminal_labeling,
baseline_parser, validation_corpus,
validationMethod)
del baseline_parser
# prepare SM training
builder = PySplitMergeTrainerBuilder(traceTrain, grammarInfo)
builder.set_em_epochs(em_epochs)
builder.set_split_randomization(1.0, seed + 1)
builder.set_simple_expector(threads=threads)
builder.set_score_validator(validator, validationDropIterations)
builder.set_smoothing_factor(smoothingFactor=smoothing_factor)
builder.set_split_randomization(percent=split_randomization)
splitMergeTrainer = builder.set_scc_merger(threshold=scc_merger_threshold,
threads=threads).build()
splitMergeTrainer.setMaxDrops(validationDropIterations, mode="smoothing")
splitMergeTrainer.setEMepochs(em_epochs, mode="smoothing")
# set initial latent annotation
latentAnnotations = []
for i in range(0, genetic_initial):
splitMergeTrainer.reset_random_seed(seed + i + 1)
la = splitMergeTrainer.split_merge_cycle(la_no_splits)
if not la.check_for_validity():
print('[Genetic] Initial LA', i,
'is not consistent! (See details before)')
if not la.is_proper():
print('[Genetic] Initial LA', i, 'is not proper!')
heapq.heappush(
latentAnnotations,
(evaluate_la(grammar, grammarInfo, la, traceValidationGenetic,
validation_genetic_corpus), i, la))
print('[Genetic] added initial LA', i)
(fBest, idBest, laBest) = min(latentAnnotations)
validation_score = evaluate_la(grammar, grammarInfo, laBest,
traceValidation, test_corpus)
print("[Genetic] Started with best F-Score (Test) of", validation_score,
"from Annotation ", idBest)
geneticCount = genetic_initial
random.seed(seed)
for round in range(1, genetic_cycles + 1):
print("[Genetic] Starting Recombination Round ", round)
# newpopulation = list(latentAnnotations)
newpopulation = []
# Cross all candidates!
for leftIndex in range(0, len(latentAnnotations)):
(fLeft, idLeft, left) = latentAnnotations[leftIndex]
# TODO: How to determine NTs to keep?
# do SM-Training
print("[Genetic] do SM-training on", idLeft, "and create LA",
geneticCount)
la = splitMergeTrainer.split_merge_cycle(la)
if not la.check_for_validity():
print(
'[Genetic] Split/Merge introduced invalid weights into LA',
geneticCount)
if not la.is_proper():
print(
'[Genetic] Split/Merge introduced problems with properness of LA',
geneticCount)
fscore = evaluate_la(grammar, grammarInfo, la,
traceValidationGenetic,
validation_genetic_corpus)
print("[Genetic] LA", geneticCount, "has F-score: ", fscore)
heapq.heappush(newpopulation, (fscore, geneticCount, la))
geneticCount += 1
heapq.heapify(newpopulation)
latentAnnotations = heapq.nsmallest(
genetic_population, heapq.merge(latentAnnotations, newpopulation))
heapq.heapify(latentAnnotations)
(fBest, idBest, laBest) = min(latentAnnotations)
validation_score = evaluate_la(grammar, grammarInfo, laBest,
traceValidation, test_corpus)
print("[Genetic] Best LA", idBest, "has F-Score (Test) of ",
validation_score)
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