基于BERT的中文序列标注python源码+项目说明.zip

# 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. """BERT finetuning runner.""" from __future__ import absolute_import from __future__ import division from __future__ import print_function import collections import csv import os import itertools import modeling import optimization import tokenization import tensorflow as tf from sklearn.metrics import classification_report flags = tf.flags FLAGS = flags.FLAGS ## Required parameters flags.DEFINE_string( "data_dir", None, "The input data dir. Should contain the .tsv files (or other data files) " "for the task.") flags.DEFINE_string( "bert_config_file", None, "The config json file corresponding to the pre-trained BERT model. " "This specifies the model architecture.") flags.DEFINE_string("task_name", None, "The name of the task to train.") flags.DEFINE_string("vocab_file", None, "The vocabulary file that the BERT model was trained on.") flags.DEFINE_string( "output_dir", None, "The output directory where the model checkpoints will be written.") ## Other parameters flags.DEFINE_string( "init_checkpoint", None, "Initial checkpoint (usually from a pre-trained BERT model).") flags.DEFINE_bool( "do_lower_case", True, "Whether to lower case the input text. Should be True for uncased " "models and False for cased models.") flags.DEFINE_integer( "max_seq_length", 128, "The maximum total input sequence length after WordPiece tokenization. " "Sequences longer than this will be truncated, and sequences shorter " "than this will be padded.") flags.DEFINE_bool("do_train", False, "Whether to run training.") flags.DEFINE_bool("do_eval", False, "Whether to run eval on the dev set.") flags.DEFINE_integer("train_batch_size", 32, "Total batch size for training.") flags.DEFINE_integer("eval_batch_size", 8, "Total batch size for eval.") flags.DEFINE_integer("pred_batch_size", 8, "Total batch size for pred.") flags.DEFINE_float("learning_rate", 5e-5, "The initial learning rate for Adam.") flags.DEFINE_float("num_train_epochs", 3.0, "Total number of training epochs to perform.") flags.DEFINE_float( "warmup_proportion", 0.1, "Proportion of training to perform linear learning rate warmup for. " "E.g., 0.1 = 10% of training.") flags.DEFINE_integer("save_checkpoints_steps", 1000, "How often to save the model checkpoint.") flags.DEFINE_integer("iterations_per_loop", 1000, "How many steps to make in each estimator call.") flags.DEFINE_bool("use_tpu", False, "Whether to use TPU or GPU/CPU.") tf.flags.DEFINE_string( "tpu_name", None, "The Cloud TPU to use for training. This should be either the name " "used when creating the Cloud TPU, or a grpc://ip.address.of.tpu:8470 " "url.") tf.flags.DEFINE_string( "tpu_zone", None, "[Optional] GCE zone where the Cloud TPU is located in. If not " "specified, we will attempt to automatically detect the GCE project from " "metadata.") tf.flags.DEFINE_string( "gcp_project", None, "[Optional] Project name for the Cloud TPU-enabled project. If not " "specified, we will attempt to automatically detect the GCE project from " "metadata.") tf.flags.DEFINE_string("master", None, "[Optional] TensorFlow master URL.") flags.DEFINE_integer( "num_tpu_cores", 8, "Only used if `use_tpu` is True. Total number of TPU cores to use.") class InputExample(object): """A single training/test example for simple sequence classification.""" def __init__(self, guid, text_a, text_b=None, label=None): """Constructs a InputExample. Args: guid: Unique id for the example. text_a: string. The untokenized text of the first sequence. For single sequence tasks, only this sequence must be specified. text_b: (Optional) string. The untokenized text of the second sequence. Only must be specified for sequence pair tasks. label: (Optional) string. The label of the example. This should be specified for train and dev examples, but not for test examples. """ self.guid = guid self.text_a = text_a self.text_b = text_b self.label = label class InputFeatures(object): """A single set of features of data.""" def __init__(self, input_ids, input_mask, segment_ids, label_id): self.input_ids = input_ids self.input_mask = input_mask self.segment_ids = segment_ids self.label_id = label_id class DataProcessor(object): """Base class for data converters for sequence classification data sets.""" def get_train_examples(self, data_dir): """Gets a collection of `InputExample`s for the train set.""" raise NotImplementedError() def get_dev_examples(self, data_dir): """Gets a collection of `InputExample`s for the dev set.""" raise NotImplementedError() def get_labels(self): """Gets the list of labels for this data set.""" raise NotImplementedError() @classmethod def _read_tsv(cls, input_file, quotechar=None): """Reads a tab separated value file.""" with tf.gfile.Open(input_file, "r") as f: reader = csv.reader(f, delimiter="\t", quotechar=quotechar) lines = [] for line in reader: lines.append(line) return lines class TeaProcessor(DataProcessor): """Processor for the TEA data set.""" def __init__(self): self.language = "zh" def get_train_examples(self, data_dir): lines = self._read_tsv(os.path.join(data_dir,'train_row__.txt')) examples = [] for (i, line) in enumerate(lines): #if i == 0: # continue guid = "train-%d" % (i) text_a = tokenization.convert_to_unicode(line[0]) label = tokenization.convert_to_unicode(line[1]) examples.append( InputExample(guid=guid, text_a=text_a, label=label)) return examples def get_dev_examples(self, data_dir): """See base class.""" lines = self._read_tsv(os.path.join(data_dir, "dev_row__.txt")) labels = [] examples = [] for (i, line) in enumerate(lines): #if i == 0: # continue guid = "dev-%d" % (i) text_a = tokenization.convert_to_unicode(line[0]) label = tokenization.convert_to_unicode(line[1]) labels.append(line[1].split(',')) examples.append( InputExample(guid=guid, text_a=text_a, label=label)) return examples, labels def get_labels(self): """See base class.""" return ["X","O", "B-R", "I-R","B-M","I-M","B-S","I-S","B-W","I-W"] def convert_single_example(ex_index, example, label_list, max_seq_length, tokenizer): """Converts a single `InputExample` into a single `InputFeatures`.""" label_map = {} for (i, label) in enumerate(label_list): label_map[label] = i tokens_a = tokenizer.tokenize(example.text_a) tokens_b = None if example.text_b: tokens_b = tokenizer.tokenize(example.text_b) if tokens_b: # Modifies `tokens_a` and `tokens_b` in place so that the total # length is less than the specified length. # Account for [CLS], [SEP], [SEP] with "- 3" _truncate_seq_pair(tokens_a, tokens_b, max_seq_length - 3) else: # Account for [CLS] and [SEP] with "- 2" if len(tokens_a) > max_seq_length - 2: tokens_a = tokens_a[0:(max_seq_length - 2)] # The convention in BERT is: # (a) For sequence pairs: # tokens: [