赞
踩
BERT(Bidirectional Encoder Representations from Transformers)是Google开发的一种新型语言模型,模型主要基于Transformer中的Encoder并加上双向的结构。
BERT的主要创新点在pre-train方法上,使用了
对话情绪识别(Emotion Detection, EmoTect),专注于识别智能对话场景中用户的情绪。针对用户文本,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。
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 # 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)
数据来自于百度飞桨团队,由两列组成,以制表符(\t
)分隔:
label–text_a
0–谁骂人了?我从来不骂人,我骂的都不是人,你是人吗 ?
1–我有事等会儿就回来和你聊
2–我见到你很高兴谢谢你帮我
# 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
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') 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)
通过BertForSequenceClassification构建用于情绪分类的BERT模型,加载预训练权重,设置情绪三分类的超参数自动构建模型。
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) 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")
在验证集上对模型验证,查看模型在验证数据上的指标。
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)
这一节对BERT模型进行了介绍,其主要创新点为Masked Language Model和Next Sentence Prediction,这两种方法可以捕获词语和句子级别的特征表示。使用预训练的BERT模型,可以很方便的对下游任务进行Fine-tuning。这一节介绍了BERT在情绪分类任务上的应用。
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。