def build_dictionary(cls,
filenames,
tokenize_func,
workers=1,
threshold=-1,
nwords=-1,
padding_factor=8):
"""Build the dictionary
Args:
filenames (list): list of filenames
workers (int): number of concurrent workers
threshold (int): defines the minimum word count
nwords (int): defines the total number of words in the final dictionary,
including special symbols
padding_factor (int): can be used to pad the dictionary size to be a
multiple of 8, which is important on some hardware (e.g., Nvidia
Tensor Cores).
"""
d = Dictionary()
for filename in filenames:
Dictionary.add_token_to_dictionary(filename, d, tokenize_func,
workers)
d.finalize(threshold=threshold,
nwords=nwords,
padding_factor=padding_factor)
return d
def build_bpe_dictionary(
cls,
filenames,
tokenize_func,
workers=1,
threshold=-1,
nwords=-1,
padding_factor=8,
**special_symbols,
):
"""Build the dictionary
Args:
filenames (list): list of filenames
workers (int): number of concurrent workers
threshold (int): defines the minimum word count
nwords (int): defines the total number of words in the final dictionary,
including special symbols
padding_factor (int): can be used to pad the dictionary size to be a
multiple of 8, which is important on some hardware (e.g., Nvidia
Tensor Cores).
"""
bpe_portion = special_symbols.get('bpe_portion', 0.5)
bpetoken_num = int(nwords * bpe_portion)
subtoken_num = nwords - bpetoken_num
# subtoken
from ncc.data import constants
subtoken_d = Dictionary(
pad=special_symbols.get('pad', constants.PAD),
bos=special_symbols.get('bos', constants.BOS),
eos=special_symbols.get('eos', constants.EOS),
unk=special_symbols.get('unk', constants.UNK),
extra_special_symbols=special_symbols.get('extra_special_symbols',
None),
)
for filename in filenames:
Dictionary.add_token_to_dictionary(filename, subtoken_d,
tokenize_func, workers)
remaining_tokens = Counter(
{sym: c
for sym, c in zip(subtoken_d.symbols, subtoken_d.count)})
subtoken_d.finalize(threshold=threshold,
nwords=subtoken_num,
padding_factor=padding_factor)
remaining_tokens = Counter({
sym: c
for sym, c in remaining_tokens.items() if sym not in subtoken_d
})
# bpetoken
from ncc.data.retrieval.word_bpe_dictionary import WordBpeDicionary
bpetoken_d = WordBpeDicionary()
bpetoken_d.learn_bpe_vocab(remaining_tokens.elements(), bpetoken_num)
bpetoken_d.finalize(threshold=0,
nwords=bpetoken_num,
padding_factor=padding_factor)
from ncc.data.retrieval.hybrid.hybrid_retrieval_dictionary import HybridRetrievalDictionary
return HybridRetrievalDictionary(subtoken_d, bpetoken_d)
def build_dictionary(
cls,
filenames,
tokenize_func,
workers=1,
threshold=-1,
nwords=-1,
padding_factor=8,
**special_symbols,
):
"""Build the dictionary
Args:
filenames (list): list of filenames
workers (int): number of concurrent workers
threshold (int): defines the minimum word count
nwords (int): defines the total number of words in the final dictionary,
including special symbols
padding_factor (int): can be used to pad the dictionary size to be a
multiple of 8, which is important on some hardware (e.g., Nvidia
Tensor Cores).
"""
from ncc.data import constants
d = Dictionary(
pad=special_symbols.get('pad', constants.PAD),
bos=special_symbols.get('bos', constants.BOS),
eos=special_symbols.get('eos', constants.EOS),
unk=special_symbols.get('unk', constants.UNK),
extra_special_symbols=special_symbols.get('extra_special_symbols',
None),
)
for filename in filenames:
Dictionary.add_token_to_dictionary(filename, d, tokenize_func,
workers)
d.finalize(threshold=threshold,
nwords=nwords,
padding_factor=padding_factor)
return d