赞
踩
%%capture captured_output
如需更换mindspore版本,可更改下面mindspore的版本号
!pip uninstall mindspore -y
!pip install -i https://pypi.mirrors.ustc.edu.cn/simple mindspore==2.2.14
# 该案例在 mindnlp 0.3.1 版本完成适配,如果发现案例跑不通,可以指定mindnlp版本,执行`!pip install mindnlp==0.3.1`
!pip install mindnlp
# 查看版本
!pip show mindspore
BERT全称是来自变换器的双向编码器表征量(Bidirectional Encoder Representations from Transformers),它是Google于2018年末开发并发布的一种新型语言模型。与BERT模型相似的预训练语言模型例如问答、命名实体识别、自然语言推理、文本分类等在许多自然语言处理任务中发挥着重要作用。模型是基于Transformer中的Encoder并加上双向的结构,因此一定要熟练掌握Transformer的Encoder的结构。
BERT模型的主要创新点都在pre-train方法上,即用了Masked Language Model和Next Sentence Prediction两种方法分别捕捉词语和句子级别的representation。
在用Masked Language Model方法训练BERT的时候,随机把语料库中15%的单词做Mask操作。对于这15%的单词做Mask操作分为三种情况:80%的单词直接用[Mask]替换、10%的单词直接替换成另一个新的单词、10%的单词保持不变。
因为涉及到Question Answering (QA) 和 Natural Language Inference (NLI)之类的任务,增加了Next Sentence Prediction预训练任务,目的是让模型理解两个句子之间的联系。与Masked Language Model任务相比,Next Sentence Prediction更简单些,训练的输入是句子A和B,B有一半的几率是A的下一句,输入这两个句子,BERT模型预测B是不是A的下一句。
BERT预训练之后,会保存它的Embedding table和12层Transformer权重(BERT-BASE)或24层Transformer权重(BERT-LARGE)。使用预训练好的BERT模型可以对下游任务进行Fine-tuning,比如:文本分类、相似度判断、阅读理解等。
对话情绪识别(Emotion Detection,简称EmoTect),专注于识别智能对话场景中用户的情绪,针对智能对话场景中的用户文本,自动判断该文本的情绪类别并给出相应的置信度,情绪类型分为积极、消极、中性。 对话情绪识别适用于聊天、客服等多个场景,能够帮助企业更好地把握对话质量、改善产品的用户交互体验,也能分析客服服务质量、降低人工质检成本。
下面以一个文本情感分类任务为例子来说明BERT模型的整个应用过程。
import os import mindspore from mindspore.dataset import text, GeneratorDataset, transforms from mindspore import nn, context from mindnlp._legacy.engine import Trainer, Evaluator from mindnlp._legacy.engine.callbacks import CheckpointCallback, BestModelCallback from mindnlp._legacy.metrics import Accuracy ''' output: Building prefix dict from the default dictionary ... Dumping model to file cache /tmp/jieba.cache Loading model cost 1.051 seconds. Prefix dict has been built successfully. ''' # prepare dataset class SentimentDataset: """Sentiment Dataset""" def __init__(self, path): self.path = path self._labels, self._text_a = [], [] self._load() def _load(self): with open(self.path, "r", encoding="utf-8") as f: dataset = f.read() lines = dataset.split("\n") for line in lines[1:-1]: label, text_a = line.split("\t") self._labels.append(int(label)) self._text_a.append(text_a) def __getitem__(self, index): return self._labels[index], self._text_a[index] def __len__(self): return len(self._labels)
# download dataset !wget https://baidu-nlp.bj.bcebos.com/emotion_detection-dataset-1.0.0.tar.gz -O emotion_detection.tar.gz !tar xvf emotion_detection.tar.gz ''' --2024-07-04 06:27:48-- https://baidu-nlp.bj.bcebos.com/emotion_detection-dataset-1.0.0.tar.gz Resolving baidu-nlp.bj.bcebos.com (baidu-nlp.bj.bcebos.com)... 119.249.103.5, 113.200.2.111, 2409:8c04:1001:1203:0:ff:b0bb:4f27 Connecting to baidu-nlp.bj.bcebos.com (baidu-nlp.bj.bcebos.com)|119.249.103.5|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 1710581 (1.6M) [application/x-gzip] Saving to: ‘emotion_detection.tar.gz’ emotion_detection.t 100%[===================>] 1.63M 241KB/s in 6.0s 2024-07-04 06:27:54 (278 KB/s) - ‘emotion_detection.tar.gz’ saved [1710581/1710581] data/ data/test.tsv data/infer.tsv data/dev.tsv data/train.tsv data/vocab.txt '''
import numpy as np def process_dataset(source, tokenizer, max_seq_len=64, batch_size=32, shuffle=True): is_ascend = mindspore.get_context('device_target') == 'Ascend' column_names = ["label", "text_a"] dataset = GeneratorDataset(source, column_names=column_names, shuffle=shuffle) # transforms type_cast_op = transforms.TypeCast(mindspore.int32) def tokenize_and_pad(text): if is_ascend: tokenized = tokenizer(text, padding='max_length', truncation=True, max_length=max_seq_len) else: tokenized = tokenizer(text) return tokenized['input_ids'], tokenized['attention_mask'] # map dataset dataset = dataset.map(operations=tokenize_and_pad, input_columns="text_a", output_columns=['input_ids', 'attention_mask']) dataset = dataset.map(operations=[type_cast_op], input_columns="label", output_columns='labels') # batch dataset if is_ascend: dataset = dataset.batch(batch_size) else: dataset = dataset.padded_batch(batch_size, pad_info={'input_ids': (None, tokenizer.pad_token_id), 'attention_mask': (None, 0)}) return dataset
from mindnlp.transformers import BertTokenizer
tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')
tokenizer.pad_token_id
# 0
dataset_train = process_dataset(SentimentDataset("data/train.tsv"), tokenizer) dataset_val = process_dataset(SentimentDataset("data/dev.tsv"), tokenizer) dataset_test = process_dataset(SentimentDataset("data/test.tsv"), tokenizer, shuffle=False) dataset_train.get_col_names() # ['input_ids', 'attention_mask', 'labels'] print(next(dataset_train.create_tuple_iterator())) ''' [Tensor(shape=[32, 64], dtype=Int64, value= [[ 101, 1511, 1435 ... 0, 0, 0], [ 101, 872, 4385 ... 0, 0, 0], [ 101, 2125, 4511 ... 0, 0, 0], ... [ 101, 5543, 2828 ... 0, 0, 0], [ 101, 2769, 2347 ... 0, 0, 0], [ 101, 7025, 4638 ... 0, 0, 0]]), Tensor(shape=[32, 64], dtype=Int64, value= [[1, 1, 1 ... 0, 0, 0], [1, 1, 1 ... 0, 0, 0], [1, 1, 1 ... 0, 0, 0], ... [1, 1, 1 ... 0, 0, 0], [1, 1, 1 ... 0, 0, 0], [1, 1, 1 ... 0, 0, 0]]), Tensor(shape=[32], dtype=Int32, value= [1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 2, 1, 1, 1, 1, 1, 0, 1, 2, 1, 0, 1, 1, 0, 1])] '''
from mindnlp.transformers import BertForSequenceClassification, BertModel from mindnlp._legacy.amp import auto_mixed_precision # set bert config and define parameters for training model = BertForSequenceClassification.from_pretrained('bert-base-chinese', num_labels=3) model = auto_mixed_precision(model, 'O1') optimizer = nn.Adam(model.trainable_params(), learning_rate=2e-5) ''' The following parameters in checkpoint files are not loaded: ['cls.predictions.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.bias', 'cls.predictions.transform.LayerNorm.weight'] The following parameters in models are missing parameter: ['classifier.weight', 'classifier.bias']''' metric = Accuracy() # define callbacks to save checkpoints ckpoint_cb = CheckpointCallback(save_path='checkpoint', ckpt_name='bert_emotect', epochs=1, keep_checkpoint_max=2) best_model_cb = BestModelCallback(save_path='checkpoint', ckpt_name='bert_emotect_best', auto_load=True) trainer = Trainer(network=model, train_dataset=dataset_train, eval_dataset=dataset_val, metrics=metric, epochs=5, optimizer=optimizer, callbacks=[ckpoint_cb, best_model_cb]) %%time # start training trainer.run(tgt_columns="labels")
evaluator = Evaluator(network=model, eval_dataset=dataset_test, metrics=metric)
evaluator.run(tgt_columns="labels")
dataset_infer = SentimentDataset("data/infer.tsv") def predict(text, label=None): label_map = {0: "消极", 1: "中性", 2: "积极"} text_tokenized = Tensor([tokenizer(text).input_ids]) logits = model(text_tokenized) predict_label = logits[0].asnumpy().argmax() info = f"inputs: '{text}', predict: '{label_map[predict_label]}'" if label is not None: info += f" , label: '{label_map[label]}'" print(info) from mindspore import Tensor for label, text in dataset_infer: predict(text, label) ''' inputs: '我 要 客观', predict: '中性' , label: '中性' inputs: '靠 你 真是 说 废话 吗', predict: '消极' , label: '消极' inputs: '口嗅 会', predict: '中性' , label: '中性' inputs: '每次 是 表妹 带 窝 飞 因为 窝路痴', predict: '中性' , label: '中性' inputs: '别说 废话 我 问 你 个 问题', predict: '消极' , label: '消极' inputs: '4967 是 新加坡 那 家 银行', predict: '中性' , label: '中性' inputs: '是 我 喜欢 兔子', predict: '积极' , label: '积极' inputs: '你 写 过 黄山 奇石 吗', predict: '中性' , label: '中性' inputs: '一个一个 慢慢来', predict: '中性' , label: '中性' inputs: '我 玩 过 这个 一点 都 不 好玩', predict: '消极' , label: '消极' inputs: '网上 开发 女孩 的 QQ', predict: '中性' , label: '中性' inputs: '背 你 猜 对 了', predict: '中性' , label: '中性' inputs: '我 讨厌 你 , 哼哼 哼 。 。', predict: '消极' , label: '消极' '''
predict("我是中国人 绝绝子叠buff") # inputs: '我是中国人 绝绝子叠buff', predict: '中性'
predict("真的太糟糕了 绝绝子叠buff") # inputs: '真的太糟糕了 绝绝子叠buff', predict: '消极'
predict("我是最棒的 绝绝子叠buff") # inputs: '我是最棒的 绝绝子叠buff', predict: '积极'
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。