def process_files(self, input_text_file, input_da_file, skip_hello=False):
"""Load DAs & sentences, obtain abstraction instructions, and store it all in member
variables (to be used later by writing methods).
@param input_text_file: path to the input file with sentences
@param input_da_file: path to the input file with DAs
@param skip_hello: skip hello() DAs (remove them from the output?)
"""
# load DAs
self._das = []
with codecs.open(input_da_file, 'r', encoding='UTF-8') as fh:
for line in fh:
self._das.append(DA.parse(line.strip()))
# load & process sentences
self._sents = []
with codecs.open(input_text_file, 'r', encoding='UTF-8') as fh:
for line in fh:
self._sents.append(self.analyze(line.strip()))
assert(len(self._das) == len(self._sents))
# skip hello() DAs, if required
if skip_hello:
pos = 0
while pos < len(self._das):
da = self._das[pos]
if len(da) == 1 and da[0].da_type == 'hello':
del self._das[pos]
del self._sents[pos]
else:
pos += 1
# delexicalize DAs and sentences
self._delex_texts()
self._delex_das()
def _init_training(self, das_file, ttree_file, data_portion):
"""Initialize training.
Store input data, initialize 1-hot feature representations for input and output and
transform training data accordingly, initialize the classification neural network.
"""
# read input
log_info('Reading DAs from ' + das_file + '...')
das = read_das(das_file)
log_info('Reading t-trees from ' + ttree_file + '...')
ttree_doc = read_ttrees(ttree_file)
trees = trees_from_doc(ttree_doc, self.language, self.selector)
# make training data smaller if necessary
train_size = int(round(data_portion * len(trees)))
self.train_trees = trees[:train_size]
self.train_das = das[:train_size]
# add empty tree + empty DA to training data
# (i.e. forbid the network to keep any of its outputs "always-on")
train_size += 1
self.train_trees.append(TreeData())
empty_da = DA.parse('inform()')
self.train_das.append(empty_da)
self.train_order = range(len(self.train_trees))
log_info('Using %d training instances.' % train_size)
# initialize input features/embeddings
if self.tree_embs:
self.dict_size = self.tree_embs.init_dict(self.train_trees)
self.X = np.array([
self.tree_embs.get_embeddings(tree)
for tree in self.train_trees
])
else:
self.tree_feats = Features(['node: presence t_lemma formeme'])
self.tree_vect = DictVectorizer(sparse=False,
binarize_numeric=True)
self.X = [
self.tree_feats.get_features(tree, {})
for tree in self.train_trees
]
self.X = self.tree_vect.fit_transform(self.X)
# initialize output features
self.da_feats = Features(['dat: dat_presence', 'svp: svp_presence'])
self.da_vect = DictVectorizer(sparse=False, binarize_numeric=True)
self.y = [
self.da_feats.get_features(None, {'da': da})
for da in self.train_das
]
self.y = self.da_vect.fit_transform(self.y)
# initialize I/O shapes
self.input_shape = [list(self.X[0].shape)]
self.num_outputs = len(self.da_vect.get_feature_names())
# initialize NN classifier
self._init_neural_network()
def process_dataset(self, input_data):
"""Load DAs & sentences, obtain abstraction instructions, and store it all in member
variables (to be used later by writing methods).
@param input_data: path to the input JSON file with the data
"""
# load data from JSON
self._das = []
self._texts = []
with codecs.open(input_data, 'r', encoding='UTF-8') as fh:
data = json.load(fh)
for inst in data:
da = DA.parse(inst['da'])
da.sort()
self._das.append(da)
self._texts.append(self.analyze(inst['text']))
# delexicalize DAs and sentences
self._create_delex_texts()
self._create_delex_das()
# return the result
out = []
for da, text, delex_da, delex_text, abst in zip(
self._das, self._texts, self._delex_das, self._delex_texts,
self._absts):
out.append(Inst(da, text, delex_da, delex_text, abst))
return out
def process_files(self, input_text_file, input_da_file, skip_hello=False):
"""Load DAs & sentences, obtain abstraction instructions, and store it all in member
variables (to be used later by writing methods).
@param input_text_file: path to the input file with sentences
@param input_da_file: path to the input file with DAs
@param skip_hello: skip hello() DAs (remove them from the output?)
"""
# load DAs
self._das = []
with codecs.open(input_da_file, 'r', encoding='UTF-8') as fh:
for line in fh:
self._das.append(DA.parse(line.strip()))
# load & process sentences
self._sents = []
with codecs.open(input_text_file, 'r', encoding='UTF-8') as fh:
for line in fh:
self._sents.append(self.analyze(line.strip()))
assert (len(self._das) == len(self._sents))
# skip hello() DAs, if required
if skip_hello:
pos = 0
while pos < len(self._das):
da = self._das[pos]
if len(da) == 1 and da[0].da_type == 'hello':
del self._das[pos]
del self._sents[pos]
else:
pos += 1
# delexicalize DAs and sentences
self._delex_texts()
self._delex_das()
def _init_training(self, das_file, ttree_file, data_portion):
"""Initialize training.
Store input data, initialize 1-hot feature representations for input and output and
transform training data accordingly, initialize the classification neural network.
"""
# read input
log_info('Reading DAs from ' + das_file + '...')
das = read_das(das_file)
log_info('Reading t-trees from ' + ttree_file + '...')
ttree_doc = read_ttrees(ttree_file)
trees = trees_from_doc(ttree_doc, self.language, self.selector)
# make training data smaller if necessary
train_size = int(round(data_portion * len(trees)))
self.train_trees = trees[:train_size]
self.train_das = das[:train_size]
# add empty tree + empty DA to training data
# (i.e. forbid the network to keep any of its outputs "always-on")
train_size += 1
self.train_trees.append(TreeData())
empty_da = DA.parse('inform()')
self.train_das.append(empty_da)
self.train_order = range(len(self.train_trees))
log_info('Using %d training instances.' % train_size)
# initialize input features/embeddings
if self.tree_embs:
self.dict_size = self.tree_embs.init_dict(self.train_trees)
self.X = np.array([self.tree_embs.get_embeddings(tree) for tree in self.train_trees])
else:
self.tree_feats = Features(['node: presence t_lemma formeme'])
self.tree_vect = DictVectorizer(sparse=False, binarize_numeric=True)
self.X = [self.tree_feats.get_features(tree, {}) for tree in self.train_trees]
self.X = self.tree_vect.fit_transform(self.X)
# initialize output features
self.da_feats = Features(['dat: dat_presence', 'svp: svp_presence'])
self.da_vect = DictVectorizer(sparse=False, binarize_numeric=True)
self.y = [self.da_feats.get_features(None, {'da': da}) for da in self.train_das]
self.y = self.da_vect.fit_transform(self.y)
# initialize I/O shapes
self.input_shape = [list(self.X[0].shape)]
self.num_outputs = len(self.da_vect.get_feature_names())
# initialize NN classifier
self._init_neural_network()
def process_files(self, input_text_file, input_da_file):
"""Load DAs & sentences, obtain abstraction instructions, and store it all in member
variables (to be used later by writing methods)."""
# load DAs
self._das = []
with codecs.open(input_da_file, 'r', encoding='UTF-8') as fh:
for line in fh:
self._das.append(DA.parse(line.strip()))
# load & process sentences
self._sents = []
with codecs.open(input_text_file, 'r', encoding='UTF-8') as fh:
for line in fh:
self._sents.append(self.analyze(line.strip()))
assert (len(self._das) == len(self._sents))
# delexicalize DAs and sentences
self._delex_texts()
self._delex_das()
def convert(args):
src = lines_to_list(args.src_file)
if args.das:
src = [DA.parse(da_text).to_cambridge_da_string() for da_text in src]
ref = lines_to_list(args.ref_file)
columns = ['mr', 'orig_ref']
df = pd.DataFrame.from_dict({'mr': src, 'orig_ref': ref})
if args.system_output:
sys = lines_to_list(args.system_output)
df['system_ref'] = sys
columns.append('system_ref')
if args.score:
score = [float(score) for score in lines_to_list(args.score)]
df['quality'] = score
columns.append('quality')
df.to_csv(args.out_file,
columns=columns,
sep=b"\t",
index=False,
encoding='UTF-8')
def _init_training(self, das, trees, data_portion):
"""Initialize training.
Store input data, initialize 1-hot feature representations for input and output and
transform training data accordingly, initialize the classification neural network.
@param das: name of source file with training DAs, or list of DAs
@param trees: name of source file with corresponding trees/sentences, or list of trees
@param data_portion: portion of the training data to be used (0.0-1.0)
"""
# read input from files or take it directly from parameters
if not isinstance(das, list):
log_info('Reading DAs from ' + das + '...')
das = read_das(das)
if not isinstance(trees, list):
log_info('Reading t-trees from ' + trees + '...')
ttree_doc = read_ttrees(trees)
if self.mode == 'tokens':
tokens = tokens_from_doc(ttree_doc, self.language,
self.selector)
trees = self._tokens_to_flat_trees(tokens)
elif self.mode == 'tagged_lemmas':
tls = tagged_lemmas_from_doc(ttree_doc, self.language,
self.selector)
trees = self._tokens_to_flat_trees(tls, use_tags=True)
else:
trees = trees_from_doc(ttree_doc, self.language, self.selector)
elif self.mode in ['tokens', 'tagged_lemmas']:
trees = self._tokens_to_flat_trees(
trees, use_tags=self.mode == 'tagged_lemmas')
# make training data smaller if necessary
train_size = int(round(data_portion * len(trees)))
self.train_trees = trees[:train_size]
self.train_das = das[:train_size]
# ignore contexts, if they are contained in the DAs
if isinstance(self.train_das[0], tuple):
self.train_das = [da for (context, da) in self.train_das]
# delexicalize if DAs are lexicalized and we don't want that
if self.delex_slots:
self.train_das = [
da.get_delexicalized(self.delex_slots) for da in self.train_das
]
# add empty tree + empty DA to training data
# (i.e. forbid the network to keep any of its outputs "always-on")
train_size += 1
self.train_trees.append(TreeData())
empty_da = DA.parse('inform()')
self.train_das.append(empty_da)
self.train_order = range(len(self.train_trees))
log_info('Using %d training instances.' % train_size)
# initialize input features/embeddings
if self.tree_embs:
self.dict_size = self.tree_embs.init_dict(self.train_trees)
self.X = np.array([
self.tree_embs.get_embeddings(tree)
for tree in self.train_trees
])
else:
self.tree_feats = Features(['node: presence t_lemma formeme'])
self.tree_vect = DictVectorizer(sparse=False,
binarize_numeric=True)
self.X = [
self.tree_feats.get_features(tree, {})
for tree in self.train_trees
]
self.X = self.tree_vect.fit_transform(self.X)
# initialize output features
self.da_feats = Features(['dat: dat_presence', 'svp: svp_presence'])
self.da_vect = DictVectorizer(sparse=False, binarize_numeric=True)
self.y = [
self.da_feats.get_features(None, {'da': da})
for da in self.train_das
]
self.y = self.da_vect.fit_transform(self.y)
log_info('Number of binary classes: %d.' %
len(self.da_vect.get_feature_names()))
# initialize I/O shapes
if not self.tree_embs:
self.input_shape = list(self.X[0].shape)
else:
self.input_shape = self.tree_embs.get_embeddings_shape()
self.num_outputs = len(self.da_vect.get_feature_names())
# initialize NN classifier
self._init_neural_network()
# initialize the NN variables
self.session.run(tf.global_variables_initializer())
def convert(args):
"""Main function – read in the JSON data and output TGEN-specific files."""
# initialize storage
items = 0
das = [] # abstracted DAs
concs = [] # concrete sentences
texts = [] # abstracted sentences
absts = [] # abstraction descriptions
contexts = [] # abstracted contexts
conc_contexts = [] # lexicalized contexts
# process the input data and store it in memory
with open(args.in_file, 'r') as fh:
data = json.load(fh, encoding='UTF-8')
for item in data:
da = convert_abstr_da(DA.parse(item['response_da']))
context = convert_abstractions(item['context_utt'])
context_l = item['context_utt_l']
conc_da = DA.parse(item['response_da_l'])
concs_ = [tokenize(s) for s in item['response_nl_l']]
absts_ = []
texts_ = []
for abst_text in item['response_nl']:
text, abst = get_abstraction(
abst_text, conc_da, args.slot_names) # convert *SLOT -> X
absts_.append(abst)
texts_.append(text)
das.append(da)
contexts.append(context)
conc_contexts.append(context_l)
concs.append(concs_)
absts.append(absts_)
texts.append(texts_)
items += 1
print 'Processed', items, 'items.'
if args.split:
# get file name prefixes and compute data sizes for all the parts to be split
out_names = re.split(r'[, ]+', args.out_name)
data_sizes = [int(part_size) for part_size in args.split.split(':')]
assert len(out_names) == len(data_sizes)
# compute sizes for all but the 1st part (+ round them)
total = float(sum(data_sizes))
remain = items
for part_no in xrange(len(data_sizes) - 1, 0, -1):
part_size = int(round(items * (data_sizes[part_no] / total)))
data_sizes[part_no] = part_size
remain -= part_size
# put whatever remained into the 1st part
data_sizes[0] = remain
else:
# use just one part -- containing all the data
data_sizes = [items]
out_names = [args.out_name]
# write all data parts
for part_size, part_name in zip(data_sizes, out_names):
repeat_num = len(concs[0])
if args.multi_ref and part_name in ['devel', 'test', 'dtest', 'etest']:
repeat_num = 1
# repeat DAs and contexts for synonymous paraphrases, unless for test data in multi-ref mode
write_part(part_name + '-das.txt', das, part_size, repeat_num)
write_part(part_name + '-context.txt', contexts, part_size, repeat_num)
write_part(part_name + '-conc_context.txt', conc_contexts, part_size,
repeat_num)
# write all other just once (here, each instance is a list, it will be unrolled)
write_part(part_name + '-conc.txt', concs, part_size)
write_part(part_name + '-abst.txt', absts, part_size)
write_part(part_name + '-text.txt', texts, part_size)
def read_sfx_data():
with codecs.open('data/sfrest-refs.tag.ngram.txt', 'r', 'UTF-8') as fh:
refs = [split_tags(inst.strip()) for inst in fh.readlines()]
with codecs.open('data/sfrest-mrs.txt', 'r', 'UTF-8') as fh:
mrs = [DA.parse(mr.strip()) for mr in fh.readlines()]
return mrs, refs
def _init_training(self, das, trees, data_portion):
"""Initialize training.
Store input data, initialize 1-hot feature representations for input and output and
transform training data accordingly, initialize the classification neural network.
@param das: name of source file with training DAs, or list of DAs
@param trees: name of source file with corresponding trees/sentences, or list of trees
@param data_portion: portion of the training data to be used (0.0-1.0)
"""
# read input from files or take it directly from parameters
if not isinstance(das, list):
log_info('Reading DAs from ' + das + '...')
das = read_das(das)
if not isinstance(trees, list):
log_info('Reading t-trees from ' + trees + '...')
ttree_doc = read_ttrees(trees)
if self.mode == 'tokens':
tokens = tokens_from_doc(ttree_doc, self.language, self.selector)
trees = self._tokens_to_flat_trees(tokens)
elif self.mode == 'tagged_lemmas':
tls = tagged_lemmas_from_doc(ttree_doc, self.language, self.selector)
trees = self._tokens_to_flat_trees(tls, use_tags=True)
else:
trees = trees_from_doc(ttree_doc, self.language, self.selector)
elif self.mode in ['tokens', 'tagged_lemmas']:
trees = self._tokens_to_flat_trees(trees, use_tags=self.mode == 'tagged_lemmas')
# make training data smaller if necessary
train_size = int(round(data_portion * len(trees)))
self.train_trees = trees[:train_size]
self.train_das = das[:train_size]
# ignore contexts, if they are contained in the DAs
if isinstance(self.train_das[0], tuple):
self.train_das = [da for (context, da) in self.train_das]
# delexicalize if DAs are lexicalized and we don't want that
if self.delex_slots:
self.train_das = [da.get_delexicalized(self.delex_slots) for da in self.train_das]
# add empty tree + empty DA to training data
# (i.e. forbid the network to keep any of its outputs "always-on")
train_size += 1
self.train_trees.append(TreeData())
empty_da = DA.parse('inform()')
self.train_das.append(empty_da)
self.train_order = range(len(self.train_trees))
log_info('Using %d training instances.' % train_size)
# initialize input features/embeddings
if self.tree_embs:
self.dict_size = self.tree_embs.init_dict(self.train_trees)
self.X = np.array([self.tree_embs.get_embeddings(tree) for tree in self.train_trees])
else:
self.tree_feats = Features(['node: presence t_lemma formeme'])
self.tree_vect = DictVectorizer(sparse=False, binarize_numeric=True)
self.X = [self.tree_feats.get_features(tree, {}) for tree in self.train_trees]
self.X = self.tree_vect.fit_transform(self.X)
# initialize output features
self.da_feats = Features(['dat: dat_presence', 'svp: svp_presence'])
self.da_vect = DictVectorizer(sparse=False, binarize_numeric=True)
self.y = [self.da_feats.get_features(None, {'da': da}) for da in self.train_das]
self.y = self.da_vect.fit_transform(self.y)
log_info('Number of binary classes: %d.' % len(self.da_vect.get_feature_names()))
# initialize I/O shapes
if not self.tree_embs:
self.input_shape = list(self.X[0].shape)
else:
self.input_shape = self.tree_embs.get_embeddings_shape()
self.num_outputs = len(self.da_vect.get_feature_names())
# initialize NN classifier
self._init_neural_network()
# initialize the NN variables
self.session.run(tf.global_variables_initializer())
def convert(args):
"""Main function – read in the JSON data and output TGEN-specific files."""
# initialize storage
items = 0
conc_das = [] # concrete DAs
das = [] # abstracted DAs
concs = [] # concrete sentences
texts = [] # abstracted sentences
absts = [] # abstraction descriptions
contexts = [] # abstracted contexts
conc_contexts = [] # lexicalized contexts
# process the input data and store it in memory
with open(args.in_file, 'r') as fh:
data = json.load(fh, encoding='UTF-8')
for item in data:
da = convert_abstr_da(DA.parse(item['response_da']))
context = convert_abstractions(item['context_utt'])
context_l = item['context_utt_l']
conc_da = DA.parse(item['response_da_l'])
concs_ = [tokenize(s) for s in item['response_nl_l']]
absts_ = []
texts_ = []
for abst_text in item['response_nl']:
text, abst = get_abstraction(abst_text, conc_da, args.slot_names) # convert *SLOT -> X
absts_.append(abst)
texts_.append(text)
das.append(da)
conc_das.append(conc_da)
contexts.append(context)
conc_contexts.append(context_l)
concs.append(concs_)
absts.append(absts_)
texts.append(texts_)
items += 1
print 'Processed', items, 'items.'
if args.split:
# get file name prefixes and compute data sizes for all the parts to be split
out_names = re.split(r'[, ]+', args.out_name)
data_sizes = [int(part_size) for part_size in args.split.split(':')]
assert len(out_names) == len(data_sizes)
# compute sizes for all but the 1st part (+ round them)
total = float(sum(data_sizes))
remain = items
for part_no in xrange(len(data_sizes) - 1, 0, -1):
part_size = int(round(items * (data_sizes[part_no] / total)))
data_sizes[part_no] = part_size
remain -= part_size
# put whatever remained into the 1st part
data_sizes[0] = remain
else:
# use just one part -- containing all the data
data_sizes = [items]
out_names = [args.out_name]
# write all data parts
for part_size, part_name in zip(data_sizes, out_names):
repeat_num = len(concs[0])
if args.multi_ref and part_name in ['devel', 'test', 'dtest', 'etest']:
repeat_num = 1
# repeat DAs and contexts for synonymous paraphrases, unless for test data in multi-ref mode
write_part(part_name + '-das.txt', das, part_size, repeat_num)
write_part(part_name + '-conc_das.txt', conc_das, part_size, repeat_num)
write_part(part_name + '-context.txt', contexts, part_size, repeat_num)
write_part(part_name + '-conc_context.txt', conc_contexts, part_size, repeat_num)
# write all other just once (here, each instance is a list, it will be unrolled)
write_part(part_name + '-ref.txt', concs, part_size, trunc=False, separate=True)
write_part(part_name + '-conc.txt', concs, part_size)
write_part(part_name + '-abst.txt', absts, part_size)
write_part(part_name + '-text.txt', texts, part_size)
