def __init__(self,
encoding_type: str = 'bio',
target_pad_val=0,
bigram=False):
if encoding_type == 'bio':
self.convert_tag = iob2
else:
self.convert_tag = lambda words: iob2bioes(iob2(words))
self.target_pad_val = int(target_pad_val)
self.bigram = bigram
def test_iob2bioes(self):
tags = [
'B-NP', 'O', 'B-NP', 'B-VP', 'B-NP', 'I-NP', 'O', 'B-NP', 'B-PP',
'B-NP', 'I-NP', 'O', 'B-NP', 'I-NP', 'B-NP', 'O', 'B-NP', 'I-NP',
'I-NP'
]
convert_tags = [
'S-NP', 'O', 'S-NP', 'S-VP', 'B-NP', 'E-NP', 'O', 'S-NP', 'S-PP',
'B-NP', 'E-NP', 'O', 'B-NP', 'E-NP', 'S-NP', 'O', 'B-NP', 'I-NP',
'E-NP'
]
self.assertSequenceEqual(convert_tags, iob2bioes(tags))
def prepare_ptb(args):
datas = {}
datas["pos"] = (ConllLoader(headers=["words", "pos"],
indexes=[0, 1]).load(args.pos).datasets)
chunk_data = (ConllLoader(headers=["words", "chunk"],
indexes=[0, 2]).load(args.chunk).datasets)
chunk_data['train'], chunk_data['dev'] = chunk_data['train'].split(0.1)
datas['chunk'] = chunk_data
datas["ner"] = (ConllLoader(headers=["words", "ner"],
indexes=[0, 3]).load(args.ner).datasets)
for ds in datas['chunk'].values():
ds.apply_field(lambda x: iob2(x), 'chunk', 'chunk')
for ds in datas['ner'].values():
ds.apply_field(lambda x: iob2bioes(iob2(x)), 'ner', 'ner')
vocabs = {}
src_vocab = Vocabulary()
for idx, task_name in enumerate(["pos", "chunk", "ner"]):
data = datas[task_name]
filter_docstart(data)
vocab = Vocabulary(padding=None, unknown=None)
vocab.from_dataset(*list(data.values()), field_name=task_name)
src_vocab.from_dataset(*list(data.values()), field_name="words")
vocabs[task_name] = vocab
task_lst = []
for idx, task_name in enumerate(["pos", "chunk", "ner"]):
data = datas[task_name]
src_vocab.index_dataset(*list(data.values()),
field_name="words",
new_field_name="words")
vocabs[task_name].index_dataset(*list(data.values()),
field_name=task_name,
new_field_name=task_name)
for ds in data.values():
ds.apply_field(len, 'words', 'seq_len')
task_lst.append(
Task(idx, task_name, data["train"], data["dev"], data["test"]))
vocabs["words"] = src_vocab
return task_lst, vocabs