笔者不久前发布过一个中文分字工具，（本文称之为version1.0）该工具是将所有的字符单独分离出来，并以空格隔开。笔者使用该工具分字之后在实体分类任务上的效果很差。原因可能有下.
时间数据经version1.0处理之后如下：
原数据：2020年4月2日
version1.0处理之后：2 0 2 0 年 4 月 2 日
这样处理可能让模型很难理解这是一个日期数据。
今天笔者将version1.0改进到version2.0，version2.0是使用Bert自带的WordPiece分词工具将文本分割成单字（英文是分词）。经version2.0处理之后日期数据会变成下面这样：
2020 年 4 月 2 日
这样模型的效果会比在version1.0分字的效果上面好很多。
以下是源码。
1.bert_token.py
import os
import sys
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "D:\work\Entity-Relation-Extraction-my\pretrained_model\chinese_L-12_H-768_A-12")))
import tokenization
'''
使用bert自带WordPiece分词工具将文本分割成单字
@Author：西兰
@Date：2020-4-1
'''
class Model_data_preparation(object):
def __init__(self, RAW_DATA_INPUT_DIR="data", DATA_OUTPUT_DIR="my_data",
vocab_file_path="vocab.txt", do_lower_case=True):
'''
:param RAW_DATA_INPUT_DIR: 输入文件目录，一般是原始数据目录
:param DATA_OUTPUT_DIR: 输出文件目录，一般是分类任务数据文件夹
:param vocab_file_path: 词表路径，一般是预先训练的模型的词表路径
:param do_lower_case: 默认TRUE
'''
# BERT 自带WordPiece分词工具，对于中文都是分成单字
self.bert_tokenizer = tokenization.FullTokenizer(vocab_file=self.get_vocab_file_path(vocab_file_path),
do_lower_case=do_lower_case) # 初始化 bert_token 工具
self.DATA_INPUT_DIR = self.get_data_input_dir(RAW_DATA_INPUT_DIR)
self.DATA_OUTPUT_DIR = os.path.join(os.path.dirname(__file__), DATA_OUTPUT_DIR)
print("数据输入路径：", self.DATA_INPUT_DIR)
print("数据输出路径：", self.DATA_OUTPUT_DIR)
# 获取输入文件路径
def get_data_input_dir(self, DATA_INPUT_DIR):
DATA_INPUT_DIR = os.path.join(
os.path.abspath(os.path.join(os.path.dirname(__file__), "../../")), DATA_INPUT_DIR)
return DATA_INPUT_DIR
# 获取词汇表路径
def get_vocab_file_path(self, vocab_file_path):
vocab_file_path = os.path.join(
os.path.abspath(os.path.join(os.path.dirname(__file__), "D:\work\Entity-Relation-Extraction-my\pretrained_model\chinese_L-12_H-768_A-12")),
vocab_file_path)
return vocab_file_path
# 处理原始数据
def separate_raw_data(self):
# if not os.path.exists(self.DATA_OUTPUT_DIR):
# os.makedirs(os.path.join(self.DATA_OUTPUT_DIR, "train"))
# os.makedirs(os.path.join(self.DATA_OUTPUT_DIR, "valid"))
# os.makedirs(os.path.join(self.DATA_OUTPUT_DIR, "test"))
token_in_f = open('./bert_raw_data_token_in.txt', "w", encoding='utf-8')
token_in_not_UNK_f = open('./bert_raw_data_token_in_not_UNK.txt', "w", encoding='utf-8')
with open('./raw_data.txt', 'r', encoding='utf-8') as f:
count_numbers = 0
while True:
line = f.readline()
if line:
count_numbers += 1
text_tokened = self.bert_tokenizer.tokenize(line)
text_tokened_not_UNK = self.bert_tokenizer.tokenize_not_UNK(line)
# print(text_tokened)
token_in_f.write(" ".join(text_tokened) + "\n")
token_in_not_UNK_f.write(" ".join(text_tokened_not_UNK) + "\n")
else:
break
print("all numbers", count_numbers)
print("\n")
token_in_f.close()
token_in_not_UNK_f.close()
if __name__ == "__main__":
RAW_DATA_DIR = "raw_data/company/all"
DATA_OUTPUT_DIR = "bert_raw_data"
bert_dir = ''
model_data = Model_data_preparation(
RAW_DATA_INPUT_DIR=RAW_DATA_DIR, DATA_OUTPUT_DIR=DATA_OUTPUT_DIR)
model_data.separate_raw_data()
2.BERT官方的tokenization.py
# coding=utf-8
# Copyright 2018 The Google AI Language Team Authors.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Tokenization classes."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import collections
import re
import unicodedata
import six
import tensorflow as tf
def validate_case_matches_checkpoint(do_lower_case, init_checkpoint):
"""Checks whether the casing config is consistent with the checkpoint name."""
# The casing has to be passed in by the user and there is no explicit check
# as to whether it matches the checkpoint. The casing information probably
# should have been stored in the bert_config.json file, but it's not, so
# we have to heuristically detect it to validate.
if not init_checkpoint:
return
m = re.match("^.*?([A-Za-z0-9_-]+)/bert_model.ckpt", init_checkpoint)
if m is None:
return
model_name = m.group(1)
lower_models = [
"uncased_L-24_H-1024_A-16", "uncased_L-12_H-768_A-12",
"multilingual_L-12_H-768_A-12", "chinese_L-12_H-768_A-12"
]
cased_models = [
"cased_L-12_H-768_A-12", "cased_L-24_H-1024_A-16",
"multi_cased_L-12_H-768_A-12"
]
is_bad_config = False
if model_name in lower_models and not do_lower_case:
is_bad_config = True
actual_flag = "False"
case_name = "lowercased"
opposite_flag = "True"
if model_name in cased_models and do_lower_case:
is_bad_config = True
actual_flag = "True"
case_name = "cased"
opposite_flag = "False"
if is_bad_config:
raise ValueError(
"You passed in `--do_lower_case=%s` with `--init_checkpoint=%s`. "
"However, `%s` seems to be a %s model, so you "
"should pass in `--do_lower_case=%s` so that the fine-tuning matches "
"how the model was pre-training. If this error is wrong, please "
"just comment out this check." % (actual_flag, init_checkpoint,
model_name, case_name, opposite_flag))
def convert_to_unicode(text):
"""Converts `text` to Unicode (if it's not already), assuming utf-8 input."""
if six.PY3:
if isinstance(text, str):
return text
elif isinstance(text, bytes):
return text.decode("utf-8", "ignore")
else:
raise ValueError("Unsupported string type: %s" % (type(text)))
elif six.PY2:
if isinstance(text, str):
return text.decode("utf-8", "ignore")
elif isinstance(text, unicode):
return text
else:
raise ValueError("Unsupported string type: %s" % (type(text)))
else:
raise ValueError("Not running on Python2 or Python 3?")
def printable_text(text):
"""Returns text encoded in a way suitable for print or `tf.logging`."""
# These functions want `str` for both Python2 and Python3, but in one case
# it's a Unicode string and in the other it's a byte string.
if six.PY3:
if isinstance(text, str):
return text
elif isinstance(text, bytes):
return text.decode("utf-8", "ignore")
else:
raise ValueError("Unsupported string type: %s" % (type(text)))
elif six.PY2:
if isinstance(text, str):
return text
elif isinstance(text, unicode):
return text.encode("utf-8")
else:
raise ValueError("Unsupported string type: %s" % (type(text)))
else:
raise ValueError("Not running on Python2 or Python 3?")
def load_vocab(vocab_file):
"""Loads a vocabulary file into a dictionary."""
vocab = collections.OrderedDict()
index = 0
with tf.gfile.GFile(vocab_file, "r") as reader:
while True:
token = convert_to_unicode(reader.readline())
if not token:
break
token = token.strip()
vocab[token] = index
index += 1
return vocab
def convert_by_vocab(vocab, items):
"""Converts a sequence of [tokens|ids] using the vocab."""
output = []
for item in items:
output.append(vocab[item])
return output
def convert_tokens_to_ids(vocab, tokens):
return convert_by_vocab(vocab, tokens)
def convert_ids_to_tokens(inv_vocab, ids):
return convert_by_vocab(inv_vocab, ids)
def whitespace_tokenize(text):
"""Runs basic whitespace cleaning and splitting on a piece of text."""
text = text.strip()
if not text:
return []
tokens = text.split()
return tokens
class FullTokenizer(object):
"""Runs end-to-end tokenziation."""
def __init__(self, vocab_file, do_lower_case=True):
self.vocab = load_vocab(vocab_file)
self.inv_vocab = {
v: k for k, v in self.vocab.items()}
self.basic_tokenizer = BasicTokenizer(do_lower_case=do_lower_case)
self.wordpiece_tokenizer = WordpieceTokenizer(vocab=self.vocab)
self.wordpiece_tokenizer_not_UNK = WordpieceTokenizer_not_UNK(vocab=self.vocab)
def tokenize(self, text):
split_tokens = []
for token in self.basic_tokenizer.tokenize(text):
for sub_token in self.wordpiece_tokenizer.tokenize(token):
split_tokens.append(sub_token)
return split_tokens
def tokenize_not_UNK(self, text):
split_tokens = []
for token in self.basic_tokenizer.tokenize(text):
for sub_token in self.wordpiece_tokenizer_not_UNK.tokenize(token):
split_tokens.append(sub_token)
return split_tokens
def convert_tokens_to_ids(self, tokens):
return convert_by_vocab(self.vocab, tokens)
def convert_ids_to_tokens(self, ids):
return convert_by_vocab(self.inv_vocab, ids)
class BasicTokenizer(object):
"""Runs basic tokenization (punctuation splitting, lower casing, etc.)."""
def __init__(self, do_lower_case=True):
"""Constructs a BasicTokenizer.
Args:
do_lower_case: Whether to lower case the input.
"""
self.do_lower_case = do_lower_case
def tokenize(self, text):
"""Tokenizes a piece of text."""
text = convert_to_unicode(text)
text = self._clean_text(text)
# This was added on November 1st, 2018 for the multilingual and Chinese
# models. This is also applied to the English models now, but it doesn't
# matter since the English models were not trained on any Chinese data
# and generally don't have any Chinese data in them (there are Chinese
# characters in the vocabulary because Wikipedia does have some Chinese
# words in the English Wikipedia.).
text = self._tokenize_chinese_chars(text)
orig_tokens = whitespace_tokenize(text)
split_tokens = []
for token in orig_tokens:
if self.do_lower_case:
token = token.lower()
token = self._run_strip_accents(token)
split_tokens.extend(self._run_split_on_punc(token))
output_tokens = whitespace_tokenize(" ".join(split_tokens))
return output_tokens
def _run_strip_accents(self, text):
"""Strips accents from a piece of text."""
text = unicodedata.normalize("NFD", text)
output = []
for char in text:
cat = unicodedata.category(char)
if cat == "Mn":
continue
output.append(char)
return "".join(output)
def _run_split_on_punc(self, text):
"""Splits punctuation on a piece of text."""
chars = list(text)
i = 0
start_new_word = True
output = []
while i < len(chars):
char = chars[i]
if _is_punctuation(char):
output.append([char])
start_new_word = True
else:
if start_new_word:
output.append([])
start_new_word = False
output[-1].append(char)
i += 1
return ["".join(x) for x in output]
def _tokenize_chinese_chars(self, text):
"""Adds whitespace around any CJK character."""
output = []
for char in text:
cp = ord(char)
if self._is_chinese_char(cp):
output.append(" ")
output.append(char)
output.append(" ")
else:
output.append(char)
return "".join(output)
def _is_chinese_char(self, cp):
"""Checks whether CP is the codepoint of a CJK character."""
# This defines a "chinese character" as anything in the CJK Unicode block:
# https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)
#
# Note that the CJK Unicode block is NOT all Japanese and Korean characters,
# despite its name. The modern Korean Hangul alphabet is a different block,
# as is Japanese Hiragana and Katakana. Those alphabets are used to write
# space-separated words, so they are not treated specially and handled
# like the all of the other languages.
if ((cp >= 0x4E00 and cp <= 0x9FFF) or #
(cp >= 0x3400 and cp <= 0x4DBF) or #
(cp >= 0x20000 and cp <= 0x2A6DF) or #
(cp >= 0x2A700 and cp <= 0x2B73F) or #
(cp >= 0x2B740 and cp <= 0x2B81F) or #
(cp >= 0x2B820 and cp <= 0x2CEAF) or
(cp >= 0xF900 and cp <= 0xFAFF) or #
(cp >= 0x2F800 and cp <= 0x2FA1F)): #
return True
return False
def _clean_text(self, text):
"""Performs invalid character removal and whitespace cleanup on text."""
output = []
for char in text:
cp = ord(char)
if cp == 0 or cp == 0xfffd or _is_control(char):
continue
if _is_whitespace(char):
output.append(" ")
else:
output.append(char)
return "".join(output)
class WordpieceTokenizer_not_UNK(object):
"""Runs WordPiece tokenziation."""
def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=200):
self.vocab = vocab
self.unk_token = unk_token
self.max_input_chars_per_word = max_input_chars_per_word
def tokenize(self, text):
"""Tokenizes a piece of text into its word pieces.
This uses a greedy longest-match-first algorithm to perform tokenization
using the given vocabulary.
For example:
input = "unaffable"
output = ["un", "##aff", "##able"]
Args:
text: A single token or whitespace separated tokens. This should have
already been passed through `BasicTokenizer.
Returns:
A list of wordpiece tokens.
"""
text = convert_to_unicode(text)
output_tokens = []
for token in whitespace_tokenize(text):
chars = list(token)
if len(chars) > self.max_input_chars_per_word:
output_tokens.append(self.unk_token)
continue
is_bad = False
start = 0
sub_tokens = []
while start < len(chars):
end = len(chars)
cur_substr = None
while start < end:
substr = "".join(chars[start:end])
if start > 0:
substr = "##" + substr
if substr in self.vocab:
cur_substr = substr
break
end -= 1
if cur_substr is None:
is_bad = True
break
sub_tokens.append(cur_substr)
start = end
if is_bad:
#output_tokens.append(self.unk_token)
output_tokens.append(token)
else:
output_tokens.extend(sub_tokens)
return output_tokens
class WordpieceTokenizer(object):
"""Runs WordPiece tokenziation."""
def __init__(self, vocab, unk_token="[UNK]", max_input_chars_per_word=200):
self.vocab = vocab
self.unk_token = unk_token
self.max_input_chars_per_word = max_input_chars_per_word
def tokenize(self, text):
"""Tokenizes a piece of text into its word pieces.
This uses a greedy longest-match-first algorithm to perform tokenization
using the given vocabulary.
For example:
input = "unaffable"
output = ["un", "##aff", "##able"]
Args:
text: A single token or whitespace separated tokens. This should have
already been passed through `BasicTokenizer.
Returns:
A list of wordpiece tokens.
"""
text = convert_to_unicode(text)
output_tokens = []
for token in whitespace_tokenize(text):
chars = list(token)
if len(chars) > self.max_input_chars_per_word:
output_tokens.append(self.unk_token)
continue
is_bad = False
start = 0
sub_tokens = []
while start < len(chars):
end = len(chars)
cur_substr = None
while start < end:
substr = "".join(chars[start:end])
if start > 0:
substr = "##" + substr
if substr in self.vocab:
cur_substr = substr
break
end -= 1
if cur_substr is None:
is_bad = True
break
sub_tokens.append(cur_substr)
start = end
if is_bad:
output_tokens.append(self.unk_token)
else:
output_tokens.extend(sub_tokens)
return output_tokens
def _is_whitespace(char):
"""Checks whether `chars` is a whitespace character."""
# \t, \n, and \r are technically contorl characters but we treat them
# as whitespace since they are generally considered as such.
if char == " " or char == "\t" or char == "\n" or char == "\r":
return True
cat = unicodedata.category(char)
if cat == "Zs":
return True
return False
def _is_control(char):
"""Checks whether `chars` is a control character."""
# These are technically control characters but we count them as whitespace
# characters.
if char == "\t" or char == "\n" or char == "\r":
return False
cat = unicodedata.category(char)
if cat.startswith("C"):
return True
return False
def _is_punctuation(char):
"""Checks whether `chars` is a punctuation character."""
cp = ord(char)
# We treat all non-letter/number ASCII as punctuation.
# Characters such as "^", "$", and "`" are not in the Unicode
# Punctuation class but we treat them as punctuation anyways, for
# consistency.
if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or
(cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)):
return True
cat = unicodedata.category(char)
if cat.startswith("P"):
return True
return False
以下是笔者的公众号，欢迎关注、投稿~
