文本相似度计算比赛-预训练模型baseline，直接上90%

该文介绍百度架构师课程内置的文本相似度计算比赛方案，用ERNIE预训练模型，将文本匹配转为分类任务，拼接query和title为输入。使用54614条训练集、7802条验证集、15604条测试集，经数据处理、模型训练，首 epoch 验证集准确率超90%，无需调参，可作基线，最后输出结果为result.csv。

☞☞☞AI 智能聊天, 问答助手, AI 智能搜索, 免费无限量使用 DeepSeek R1 模型☜☜☜

文本相似度计算比赛-使用预训练模型，直接上90%

比赛是百度架构师手把手带你零基础实践深度学习课程内置的比赛,似乎已经停止判分了.
训练集:54614条
验证集:7802条
测试集:15604条
本文改自『NLP经典项目集』02：使用预训练模型ERNIE优化情感分析
没有任何调参，所以作为预训练模型的baseline完全没问题

1. 任务介绍

1.1 任务内容

文本语义匹配是自然语言处理中一个重要的基础问题，NLP领域的很多任务都可以抽象为文本匹配任务。例如，信息检索可以归结为查询项和文档的匹配，问答系统可以归结为问题和候选答案的匹配，对话系统可以归结为对话和回复的匹配。语义匹配在搜索优化、推荐系统、快速检索排序、智能客服上都有广泛的应用。如何提升文本匹配的准确度，是自然语言处理领域的一个重要挑战。

信息检索：在信息检索领域的很多应用中，都需要根据原文本来检索与其相似的其他文本，使用场景非常普遍。新闻推荐：通过用户刚刚浏览过的新闻标题，自动检索出其他的相似新闻，个性化地为用户做推荐，从而增强用户粘性，提升产品体验。智能客服：用户输入一个问题后，自动为用户检索出相似的问题和答案，节约人工客服的成本，提高效率。

1.2 什么是文本匹配？

让我们来看一个简单的例子，比较各候选句子哪句和原句语义更相近

原句：“车头如何放置车牌”

比较句1：“前牌照怎么装”比较句2：“如何办理北京车牌”比较句3：“后牌照怎么装”

（1）比较句1与原句，虽然句式和语序等存在较大差异，但是所表述的含义几乎相同

（2）比较句2与原句，虽然存在“如何” 、“车牌”等共现词，但是所表述的含义完全不同

（3）比较句3与原句，二者讨论的都是如何放置车牌的问题，只不过一个是前牌照，另一个是后牌照。二者间存在一定的语义相关性。

所以语义相关性，句1大于句3，句3大于句2.这就是语义匹配。

1.3 使用预训练序列分类模型

本任务本是匹配工作，两个距离相似则是1，不相似则是0.这其实也可以看做一个分类任务，两个句子是相似的，则类别为1，两个句子不相似的，则类别为0.

本文使用的是一个文本分类的例子『NLP经典项目集』02：使用预训练模型ERNIE优化情感分析

通读全文后会发现，我们的主要任务其实变成了如何构建这样一句话，这里使用最简单的做法，直接将两个句子拼接
即，query和title直接拼接。        

加载第三方库，paddle和paddlenlp相关的库

In [ ]

import mathimport numpy as npimport osimport collectionsfrom functools import partialimport randomimport timeimport inspectimport importlibfrom tqdm import tqdmimport paddleimport paddle.nn as nnimport paddle.nn.functional as Ffrom paddle.io import IterableDatasetfrom paddle.utils.download import get_path_from_url

本实验需要依赖与paddlenlp，aistudio上的paddlenlp版本过低，所以需要首先升级paddlenlp

In [ ]

!pip install paddlenlp --upgrade

导入paddlenlp相关的包

In [ ]

import paddlenlp as ppnlpfrom paddlenlp.data import JiebaTokenizer, Pad, Stack, Tuple, Vocab# from utils import convert_examplefrom paddlenlp.datasets import MapDatasetfrom paddle.dataset.common import md5filefrom paddlenlp.datasets import DatasetBuilder

2. 定义模型和tokenizer

2.1 定义模型预训练

经过前面的分析,我们将两个句子拼成了一句话,然后转变成分类任务,所以这里使用序列分类模型.这里其实主要用的是model,那个ernie_model是为了帮助理解展示用的.

In [ ]

MODEL_NAME = "ernie-1.0"ernie_model = ppnlp.transformers.ErnieModel.from_pretrained(MODEL_NAME)model = ppnlp.transformers.ErnieForSequenceClassification.from_pretrained(MODEL_NAME, num_classes=2)

[2021-05-18 10:21:29,970] [    INFO] - Downloading https://paddlenlp.bj.bcebos.com/models/transformers/ernie/ernie_v1_chn_base.pdparams and saved to /home/aistudio/.paddlenlp/models/ernie-1.0[2021-05-18 10:21:29,973] [    INFO] - Downloading ernie_v1_chn_base.pdparams from https://paddlenlp.bj.bcebos.com/models/transformers/ernie/ernie_v1_chn_base.pdparams100%|██████████| 392507/392507 [00:09<00:00, 43038.06it/s][2021-05-18 10:21:45,369] [    INFO] - Weights from pretrained model not used in ErnieModel: ['cls.predictions.layer_norm.weight', 'cls.predictions.decoder_bias', 'cls.predictions.transform.bias', 'cls.predictions.transform.weight', 'cls.predictions.layer_norm.bias'][2021-05-18 10:21:45,675] [    INFO] - Already cached /home/aistudio/.paddlenlp/models/ernie-1.0/ernie_v1_chn_base.pdparams/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1297: UserWarning: Skip loading for classifier.weight. classifier.weight is not found in the provided dict.  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/fluid/dygraph/layers.py:1297: UserWarning: Skip loading for classifier.bias. classifier.bias is not found in the provided dict.  warnings.warn(("Skip loading for {}. ".format(key) + str(err)))

2.2 定义一个模型对应的tokenizer

In [ ]

tokenizer = ppnlp.transformers.ErnieTokenizer.from_pretrained(MODEL_NAME)

[2021-05-18 10:21:47,430] [    INFO] - Downloading vocab.txt from https://paddlenlp.bj.bcebos.com/models/transformers/ernie/vocab.txt100%|██████████| 90/90 [00:00<00:00, 4144.52it/s]

按照官方例子，测试一下我们的句子吧

In [ ]

tokens = tokenizer._tokenize("万家乐燃气热水器怎么样")print("Tokens: {}".format(tokens))# token映射为对应token idtokens_ids = tokenizer.convert_tokens_to_ids(tokens)print("Tokens id: {}".format(tokens_ids))# 拼接上预训练模型对应的特殊token ，如[CLS]、[SEP]tokens_ids = tokenizer.build_inputs_with_special_tokens(tokens_ids)print("Tokens id: {}".format(tokens_ids))# 转化成paddle框架数据格式tokens_pd = paddle.to_tensor([tokens_ids])print("Tokens : {}".format(tokens_pd))# 此时即可输入ERNIE模型中得到相应输出sequence_output, pooled_output = ernie_model(tokens_pd)print("Token wise output: {}, Pooled output: {}".format(sequence_output.shape, pooled_output.shape))

Tokens: ['万', '家', '乐', '燃', '气', '热', '水', '器', '怎', '么', '样']Tokens id: [211, 50, 354, 1404, 266, 506, 101, 361, 936, 356, 314]Tokens id: [1, 211, 50, 354, 1404, 266, 506, 101, 361, 936, 356, 314, 2]Tokens : Tensor(shape=[1, 13], dtype=int64, place=CUDAPlace(0), stop_gradient=True,       [[1  , 211, 50 , 354, 1404, 266, 506, 101, 361, 936, 356, 314, 2  ]])Token wise output: [1, 13, 768], Pooled output: [1, 768]

/opt/conda/envs/python35-paddle120-env/lib/python3.7/site-packages/paddle/tensor/creation.py:143: DeprecationWarning: `np.object` is a deprecated alias for the builtin `object`. To silence this warning, use `object` by itself. Doing this will not modify any behavior and is safe. Deprecated in NumPy 1.20; for more details and guidance: https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations  if data.dtype == np.object:

       In [ ]

encoded_text = tokenizer(text="万家乐燃气热水器怎么样",  max_seq_len=20)for key, value in encoded_text.items():    print("{}:nt{}".format(key, value))# 转化成paddle框架数据格式input_ids = paddle.to_tensor([encoded_text['input_ids']])print("input_ids : {}".format(input_ids))segment_ids = paddle.to_tensor([encoded_text['token_type_ids']])print("token_type_ids : {}".format(segment_ids))# 此时即可输入ERNIE模型中得到相应输出sequence_output, pooled_output = ernie_model(input_ids, segment_ids)print("Token wise output: {}, Pooled output: {}".format(sequence_output.shape, pooled_output.shape))

input_ids:[1, 211, 50, 354, 1404, 266, 506, 101, 361, 936, 356, 314, 2]token_type_ids:[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]input_ids : Tensor(shape=[1, 13], dtype=int64, place=CUDAPlace(0), stop_gradient=True,       [[1  , 211, 50 , 354, 1404, 266, 506, 101, 361, 936, 356, 314, 2  ]])token_type_ids : Tensor(shape=[1, 13], dtype=int64, place=CUDAPlace(0), stop_gradient=True,       [[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]])Token wise output: [1, 13, 768], Pooled output: [1, 768]

3. 数据读取

3.1 load_dataset函数

本实验共计需要读取四份数据: 训练集 train.tsv、验证集 dev.tsv、测试集 test.tsv 和 词汇表 vocab.txt。加载数据的代码如下： 这里是课程提供的，不需要修改

In [ ]

class BAIDUData2(DatasetBuilder):    SPLITS = {        # 'train':os.path.join('data', 'baidu_train.tsv'),        # 'dev': os.path.join('data', 'baidu_dev.tsv'),        'train': 'baidu_train.tsv',        'dev': 'baidu_dev.tsv',    }    def _get_data(self, mode, **kwargs):        filename = self.SPLITS[mode]        return filename    def _read(self, filename):        """读取数据"""        with open(filename, 'r', encoding='utf-8') as f:            head = None            for line in f:                data = line.strip().split("t")                if not head:                    head = data                else:                    query, title, label = data                    yield {"query": query, "title": title, "label": label}    def get_labels(self):        return ["0", "1"]

   In [ ]

def load_dataset(name=None,                 data_files=None,                 splits=None,                 lazy=None,                 **kwargs):       reader_cls = BAIDUData2    print(reader_cls)    if not name:        reader_instance = reader_cls(lazy=lazy, **kwargs)    else:        reader_instance = reader_cls(lazy=lazy, name=name, **kwargs)    datasets = reader_instance.read_datasets(data_files=data_files, splits=splits)    return datasets

   In [ ]

# Loads dataset.train_ds, dev_ds = load_dataset(splits=["train", "dev"])

3.2 前处理:拼接句子

主要针对我们的任务，修改convert_example函数，在这个里面，将query和title拼接，并转成token，convert_example这个在utils.py中123行

In [ ]

from functools import partialfrom paddlenlp.data import Stack, Tuple, Padfrom utils import  convert_example, create_dataloaderbatch_size = 32max_seq_length = 128trans_func = partial(    convert_example,    tokenizer=tokenizer,    max_seq_length=max_seq_length)batchify_fn = lambda samples, fn=Tuple(    Pad(axis=0, pad_val=tokenizer.pad_token_id),  # input    Pad(axis=0, pad_val=tokenizer.pad_token_type_id),  # segment    Stack(dtype="int64")  # label): [data for data in fn(samples)]

   In [ ]

train_data_loader = create_dataloader(    train_ds,    mode='train',    batch_size=batch_size,    batchify_fn=batchify_fn,    trans_fn=trans_func)dev_data_loader = create_dataloader(    dev_ds,    mode='dev',    batch_size=batch_size,    batchify_fn=batchify_fn,    trans_fn=trans_func)

4. 定义一些超参，loss，优化器等

In [ ]

from paddlenlp.transformers import LinearDecayWithWarmup# 训练过程中的最大学习率learning_rate = 5e-5 # 训练轮次epochs = 4# 学习率预热比例warmup_proportion = 0.1# 权重衰减系数，类似模型正则项策略，避免模型过拟合weight_decay = 0.01num_training_steps = len(train_data_loader) * epochslr_scheduler = LinearDecayWithWarmup(learning_rate, num_training_steps, warmup_proportion)optimizer = paddle.optimizer.AdamW(    learning_rate=lr_scheduler,    parameters=model.parameters(),    weight_decay=weight_decay,    apply_decay_param_fun=lambda x: x in [        p.name for n, p in model.named_parameters()        if not any(nd in n for nd in ["bias", "norm"])    ])criterion = paddle.nn.loss.CrossEntropyLoss()metric = paddle.metric.Accuracy()

5. 开始训练，可以看到第一个epoch在eval上就上90%了

In [12]

import paddle.nn.functional as Ffrom utils import evaluateglobal_step = 0for epoch in range(1, epochs + 1):    for step, batch in enumerate(train_data_loader, start=1):        input_ids, segment_ids, labels = batch        logits = model(input_ids, segment_ids)        loss = criterion(logits, labels)        probs = F.softmax(logits, axis=1)        correct = metric.compute(probs, labels)        metric.update(correct)        acc = metric.accumulate()        global_step += 1        if global_step % 10 == 0 :            print("global step %d, epoch: %d, batch: %d, loss: %.5f, acc: %.5f" % (global_step, epoch, step, loss, acc))        loss.backward()        optimizer.step()        lr_scheduler.step()        optimizer.clear_grad()    evaluate(model, criterion, metric, dev_data_loader)

保存模型

In [ ]

model.save_pretrained('checkpoint2')tokenizer.save_pretrained('checkpoint2')

6.测试结果，输出csv

In [ ]

from utils import predictimport pandas as pdlabel_map = {0:'0', 1:'1'}def preprocess_prediction_data(data):    examples = []    for query, title in data:        examples.append({"query": query, "title": title})        #print(len(examples),': ',query,"---", title)    return examplestest_file = 'test_forstu.tsv'data = pd.read_csv(test_file, sep='t')#print(data.shape)data1 = list(data.values)examples = preprocess_prediction_data(data1)

   In [ ]

results = predict(        model, examples, tokenizer, label_map, batch_size=batch_size)for idx, text in enumerate(examples):    print('Data: {} t Label: {}'.format(text, results[idx]))data2 = []for i in range(len(data1)):    data2.extend(results[i])data['label'] = data2print(data.shape)data.to_csv('result.csv',sep='t')

最后提交结果就生成的result.csv文件就可以啦.

以上就是文本相似度计算比赛-预训练模型baseline，直接上90%的详细内容，更多请关注创想鸟其它相关文章！