Datawhale AI夏令营--NLP方向:多语言机器翻译模型的构建与训练之Seq2Seq (2)--[基于术语词典干预的机器翻译挑战赛]-CSDN博客

本文链接：https://blog.csdn.net/m0_56875011/article/details/140469796

一、Seq2Seq模型是什么？

Seq2Seq模型是一种深度学习架构，‌专为处理从一个输入序列到一个输出序列的映射任务设计。‌ 这种模型最初应用于机器翻译任务，‌但因其灵活性和有效性，‌现已被广泛应用于自然语言处理(NLP)、‌语音识别、‌图像描述生成、‌对话系统、‌文本摘要等众多领域中涉及序列转换的问题。‌

Seq2Seq模型基于Encoder-Decoder（‌编码器-解码器）‌框架的神经网络模型，‌其中编码器和解码器可以是一层或多层RNN、‌LSTM、‌GRU等神经网络。‌编码器通过编码输入序列获得语义编码C，‌解码器通过解码C获得输出序列。‌这种模型允许输入和输出序列的长度不同，‌提供了处理变长序列的能力。‌

Seq2Seq模型的发展经历了从基本的Encoder-Decoder结构到引入注意力机制（‌Attention）‌的阶段。‌注意力机制的加入使得模型在每一步解码时都能有针对性地关注输入序列的不同部分，‌从而提高了解码的效果和模型的性能。‌这种结合了注意力机制的Seq2Seq模型在自然语言翻译、‌人机对话等领域得到了广泛的应用，‌并进一步拓展到其他需要序列转换的任务中。‌

二、基于 Seq2Seq 的 Baseline 详解

1、环境配置

运行环境我们还是基于魔搭平台进行模型训练，这里不再重复说明。另外，有几个包需要额外安装：

torchtext ：是一个用于自然语言处理（NLP）任务的库，它提供了丰富的功能，包括数据预处理、词汇构建、序列化和批处理等，特别适合于文本分类、情感分析、机器翻译等任务
jieba：是一个中文分词库，用于将中文文本切分成有意义的词语
sacrebleu：用于评估机器翻译质量的工具，主要通过计算BLEU（Bilingual Evaluation Understudy）得分来衡量生成文本与参考译文之间的相似度。
spacy：是一个强大的自然语言处理库，支持70+语言的分词与训练

相关代码

!pip install torchtext
!pip install jieba
!pip install sacrebleu

!pip install -U pip setuptools wheel -i https://pypi.tuna.tsinghua.edu.cn/simple
!pip install -U 'spacy[cuda12x]' -i https://pypi.tuna.tsinghua.edu.cn/simple
!pip install ../dataset/en_core_web_trf-3.7.3-py3-none-any.whl

en_core_web_trf-3.7.3-py3-none-any.whl 文件的下载

因为spacy 的版本有较强的依赖性。通过代码pip show spacy查看你的版本，可以看到我的是 3.7.5 版本的 spacy。

下载链接：

https://github.com/explosion/spacy-models/releases

2、数据预处理

清洗和规范化数据
- 去除无关信息：删除HTML标签、特殊字符、非文本内容等，确保文本的纯净性（本赛题的训练集中出现了非常多的脏数据，如“Joey. （掌声）（掌声）乔伊”、“Thank you. （马嘶声）谢谢你们”等这种声音词）
- 统一格式：转换所有文本为小写，确保一致性；标准化日期、数字等格式。
- 分句和分段：将长文本分割成句子或段落，便于处理和训练。
分词
- 分词：将句子分解成单词或词素（构成单词的基本组成部分，一个词素可以是一个完整的单词，也可以是单词的一部分，但每一个词素都至少携带一部分语义或语法信息），这是NLP中最基本的步骤之一。我们这里使用了使用jieba 对中文进行分词，使用spaCy对英文进行分词。
构建词汇表和词向量
- 词汇表构建：从训练数据中收集所有出现过的词汇，构建词汇表，并为每个词分配一个唯一的索引。
- 词向量：使用预训练的词向量或自己训练词向量，将词汇表中的词映射到高维空间中的向量，以捕捉语义信息（当前大模型领域训练的 embedding 模型就是用来完成此任务的）。
序列截断和填充
- 序列截断：限制输入序列的长度，过长的序列可能增加计算成本，同时也可能包含冗余信息。
- 序列填充：将所有序列填充至相同的长度，便于批量处理。通常使用<PAD>标记填充。
添加特殊标记
- 序列开始和结束标记：在序列两端添加<SOS>（Sequence Start）和<EOS>（Sequence End）标记，帮助模型识别序列的起始和结束。
- 未知词标记：为不在词汇表中的词添加<UNK>（Unknown）标记，使模型能够处理未见过的词汇。
数据增强
- 随机替换或删除词：在训练数据中随机替换或删除一些词，增强模型的鲁棒性。
- 同义词替换：使用同义词替换原文中的词，增加训练数据的多样性。
数据分割
- 划分数据集：将数据划分为训练集、验证集和测试集，分别用于模型训练、参数调整和最终性能评估（该赛题中已划分好，不需要自己进行划分）

# 定义tokenizer
en_tokenizer = get_tokenizer('spacy', language='en_core_web_trf')
zh_tokenizer = lambda x: list(jieba.cut(x))  # 使用jieba分词

# 读取数据函数
def read_data(file_path: str) -> List[str]:
    with open(file_path, 'r', encoding='utf-8') as f:
        return [line.strip() for line in f]

# 数据预处理函数
def preprocess_data(en_data: List[str], zh_data: List[str]) -> List[Tuple[List[str], List[str]]]:
    processed_data = []
    for en, zh in zip(en_data, zh_data):
        en_tokens = en_tokenizer(en.lower())[:MAX_LENGTH]
        zh_tokens = zh_tokenizer(zh)[:MAX_LENGTH]
        if en_tokens and zh_tokens:  # 确保两个序列都不为空
            processed_data.append((en_tokens, zh_tokens))
    return processed_data

# 构建词汇表
def build_vocab(data: List[Tuple[List[str], List[str]]]):
    en_vocab = build_vocab_from_iterator(
        (en for en, _ in data),
        specials=['<unk>', '<pad>', '<bos>', '<eos>']
    )
    zh_vocab = build_vocab_from_iterator(
        (zh for _, zh in data),
        specials=['<unk>', '<pad>', '<bos>', '<eos>']
    )
    en_vocab.set_default_index(en_vocab['<unk>'])
    zh_vocab.set_default_index(zh_vocab['<unk>'])
    return en_vocab, zh_vocab


class TranslationDataset(Dataset):
    def __init__(self, data: List[Tuple[List[str], List[str]]], en_vocab, zh_vocab):
        self.data = data
        self.en_vocab = en_vocab
        self.zh_vocab = zh_vocab

    def __len__(self):
        return len(self.data)

    def __getitem__(self, idx):
        en, zh = self.data[idx]
        en_indices = [self.en_vocab['<bos>']] + [self.en_vocab[token] for token in en] + [self.en_vocab['<eos>']]
        zh_indices = [self.zh_vocab['<bos>']] + [self.zh_vocab[token] for token in zh] + [self.zh_vocab['<eos>']]
        return en_indices, zh_indices

def collate_fn(batch):
    en_batch, zh_batch = [], []
    for en_item, zh_item in batch:
        if en_item and zh_item:  # 确保两个序列都不为空
            # print("都不为空")
            en_batch.append(torch.tensor(en_item))
            zh_batch.append(torch.tensor(zh_item))
        else:
            print("存在为空")
    if not en_batch or not zh_batch:  # 如果整个批次为空，返回空张量
        return torch.tensor([]), torch.tensor([])
    
    # src_sequences = [item[0] for item in batch]
    # trg_sequences = [item[1] for item in batch]
    
    en_batch = nn.utils.rnn.pad_sequence(en_batch, batch_first=True, padding_value=en_vocab['<pad>'])
    zh_batch = nn.utils.rnn.pad_sequence(zh_batch, batch_first=True, padding_value=zh_vocab['<pad>'])

    # en_batch = pad_sequence(en_batch, batch_first=True, padding_value=en_vocab['<pad>'])
    # zh_batch = pad_sequence(zh_batch, batch_first=True, padding_value=zh_vocab['<pad>'])
    
    return en_batch, zh_batch

# 数据加载函数
def load_data(train_path: str, dev_en_path: str, dev_zh_path: str, test_en_path: str):
    # 读取训练数据
    train_data = read_data(train_path)
    train_en, train_zh = zip(*(line.split('\t') for line in train_data))
    
    # 读取开发集和测试集
    dev_en = read_data(dev_en_path)
    dev_zh = read_data(dev_zh_path)
    test_en = read_data(test_en_path)

    # 预处理数据
    train_processed = preprocess_data(train_en, train_zh)
    dev_processed = preprocess_data(dev_en, dev_zh)
    test_processed = [(en_tokenizer(en.lower())[:MAX_LENGTH], []) for en in test_en if en.strip()]

    # 构建词汇表
    global en_vocab, zh_vocab
    en_vocab, zh_vocab = build_vocab(train_processed)

    # 创建数据集
    train_dataset = TranslationDataset(train_processed, en_vocab, zh_vocab)
    dev_dataset = TranslationDataset(dev_processed, en_vocab, zh_vocab)
    test_dataset = TranslationDataset(test_processed, en_vocab, zh_vocab)
    
    from torch.utils.data import Subset

    # 假设你有10000个样本，你只想用前1000个样本进行测试
    indices = list(range(N))
    train_dataset = Subset(train_dataset, indices)

    # 创建数据加载器
    train_loader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_fn, drop_last=True)
    dev_loader = DataLoader(dev_dataset, batch_size=BATCH_SIZE, collate_fn=collate_fn, drop_last=True)
    test_loader = DataLoader(test_dataset, batch_size=BATCH_SIZE, collate_fn=collate_fn, drop_last=True)

    return train_loader, dev_loader, test_loader, en_vocab, zh_vocab

3、模型构建


class Encoder(nn.Module):
    def __init__(self, input_dim, emb_dim, hid_dim, n_layers, dropout):
        super().__init__()
        self.hid_dim = hid_dim
        self.n_layers = n_layers
        
        self.embedding = nn.Embedding(input_dim, emb_dim)
        self.gru = nn.GRU(emb_dim, hid_dim, n_layers, dropout=dropout, batch_first=True)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, src):
        # src = [batch size, src len]
        embedded = self.dropout(self.embedding(src))
        # embedded = [batch size, src len, emb dim]
        
        outputs, hidden = self.gru(embedded)
        # outputs = [batch size, src len, hid dim * n directions]
        # hidden = [n layers * n directions, batch size, hid dim]
        
        return outputs, hidden

class Attention(nn.Module):
    def __init__(self, hid_dim):
        super().__init__()
        self.attn = nn.Linear(hid_dim * 2, hid_dim)
        self.v = nn.Linear(hid_dim, 1, bias=False)
        
    def forward(self, hidden, encoder_outputs):
        # hidden = [1, batch size, hid dim]
        # encoder_outputs = [batch size, src len, hid dim]
        
        batch_size = encoder_outputs.shape[0]
        src_len = encoder_outputs.shape[1]
        
        hidden = hidden.repeat(src_len, 1, 1).transpose(0, 1)
        # hidden = [batch size, src len, hid dim]
        
        energy = torch.tanh(self.attn(torch.cat((hidden, encoder_outputs), dim=2)))
        # energy = [batch size, src len, hid dim]
        
        attention = self.v(energy).squeeze(2)
        # attention = [batch size, src len]
        
        return F.softmax(attention, dim=1)

class Decoder(nn.Module):
    def __init__(self, output_dim, emb_dim, hid_dim, n_layers, dropout, attention):
        super().__init__()
        self.output_dim = output_dim
        self.hid_dim = hid_dim
        self.n_layers = n_layers
        self.attention = attention
        
        self.embedding = nn.Embedding(output_dim, emb_dim)
        self.gru = nn.GRU(hid_dim + emb_dim, hid_dim, n_layers, dropout=dropout, batch_first=True)
        self.fc_out = nn.Linear(hid_dim * 2 + emb_dim, output_dim)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, input, hidden, encoder_outputs):
        # input = [batch size, 1]
        # hidden = [n layers, batch size, hid dim]
        # encoder_outputs = [batch size, src len, hid dim]
        
        input = input.unsqueeze(1)
        embedded = self.dropout(self.embedding(input))
        # embedded = [batch size, 1, emb dim]
        
        a = self.attention(hidden[-1:], encoder_outputs)
        # a = [batch size, src len]
        
        a = a.unsqueeze(1)
        # a = [batch size, 1, src len]
        
        weighted = torch.bmm(a, encoder_outputs)
        # weighted = [batch size, 1, hid dim]
        
        rnn_input = torch.cat((embedded, weighted), dim=2)
        # rnn_input = [batch size, 1, emb dim + hid dim]
        
        output, hidden = self.gru(rnn_input, hidden)
        # output = [batch size, 1, hid dim]
        # hidden = [n layers, batch size, hid dim]
        
        embedded = embedded.squeeze(1)
        output = output.squeeze(1)
        weighted = weighted.squeeze(1)
        
        prediction = self.fc_out(torch.cat((output, weighted, embedded), dim=1))
        # prediction = [batch size, output dim]
        
        return prediction, hidden

class Seq2Seq(nn.Module):
    def __init__(self, encoder, decoder, device):
        super().__init__()
        self.encoder = encoder
        self.decoder = decoder
        self.device = device
        
    def forward(self, src, trg, teacher_forcing_ratio=0.5):
        # src = [batch size, src len]
        # trg = [batch size, trg len]
        
        batch_size = src.shape[0]
        trg_len = trg.shape[1]
        trg_vocab_size = self.decoder.output_dim
        
        outputs = torch.zeros(batch_size, trg_len, trg_vocab_size).to(self.device)
        encoder_outputs, hidden = self.encoder(src)
        
        input = trg[:, 0]
        
        for t in range(1, trg_len):
            output, hidden = self.decoder(input, hidden, encoder_outputs)
            outputs[:, t] = output
            teacher_force = random.random() < teacher_forcing_ratio
            top1 = output.argmax(1)
            input = trg[:, t] if teacher_force else top1
        
        return outputs


# 初始化模型
def initialize_model(input_dim, output_dim, emb_dim, hid_dim, n_layers, dropout, device):
    attn = Attention(hid_dim)
    enc = Encoder(input_dim, emb_dim, hid_dim, n_layers, dropout)
    dec = Decoder(output_dim, emb_dim, hid_dim, n_layers, dropout, attn)
    model = Seq2Seq(enc, dec, device).to(device)
    return model

4、训练模型

神经机器翻译就不得不提编码器-解码器模型，或编码器-解码器框架（EncoderDecoder Paradigm）。本质上，编码器解码器模型是描述输入输出之间关系的一种方式。编码器解码器这个概念在日常生活中并不少见。

这种“先编码，再解码”的思想被应用到密码学、信息论等多个领域。不难看出，机器翻译问题也完美的贴合编码器解码器结构的特点。可以将源语言编码为类似信息传输中的数字信号，然后利用解码器对其进行转换，生成目标语言。下面就来看一下神经机器翻译是如何在编码器解码器框架下进行工作的。

下面是一个应用编码器解码器结构来解决汉译英的例子：

# 定义优化器
def initialize_optimizer(model, learning_rate=0.001):
    return optim.Adam(model.parameters(), lr=learning_rate)

# 运行时间
def epoch_time(start_time, end_time):
    elapsed_time = end_time - start_time
    elapsed_mins = int(elapsed_time / 60)
    elapsed_secs = int(elapsed_time - (elapsed_mins * 60))
    return elapsed_mins, elapsed_secs

def train(model, iterator, optimizer, criterion, clip):
    model.train()
    epoch_loss = 0
    
    for i, batch in enumerate(iterator):
        #print(f"Training batch {i}")
        src, trg = batch
        #print(f"Source shape before: {src.shape}, Target shape before: {trg.shape}")
        if src.numel() == 0 or trg.numel() == 0:
            #print("Empty batch detected, skipping...")
            continue  # 跳过空的批次
        
        src, trg = src.to(DEVICE), trg.to(DEVICE)
        
        optimizer.zero_grad()
        output = model(src, trg)
        
        output_dim = output.shape[-1]
        output = output[:, 1:].contiguous().view(-1, output_dim)
        trg = trg[:, 1:].contiguous().view(-1)
        
        loss = criterion(output, trg)
        loss.backward()
        
        clip_grad_norm_(model.parameters(), clip)
        optimizer.step()
        
        epoch_loss += loss.item()

    print(f"Average loss for this epoch: {epoch_loss / len(iterator)}")
    return epoch_loss / len(iterator)

def evaluate(model, iterator, criterion):
    model.eval()
    epoch_loss = 0
    with torch.no_grad():
        for i, batch in enumerate(iterator):
            #print(f"Evaluating batch {i}")
            src, trg = batch
            if src.numel() == 0 or trg.numel() == 0:
                continue  # 跳过空批次
            
            src, trg = src.to(DEVICE), trg.to(DEVICE)
            
            output = model(src, trg, 0)  # 关闭 teacher forcing
            
            output_dim = output.shape[-1]
            output = output[:, 1:].contiguous().view(-1, output_dim)
            trg = trg[:, 1:].contiguous().view(-1)
            
            loss = criterion(output, trg)
            epoch_loss += loss.item()
        
    return epoch_loss / len(iterator)

# 翻译函数
def translate_sentence(src_indexes, src_vocab, tgt_vocab, model, device, max_length=50):
    model.eval()
    
    src_tensor = src_indexes.unsqueeze(0).to(device)  # 添加批次维度
    
    # with torch.no_grad():
    #     encoder_outputs = model.encoder(model.positional_encoding(model.src_embedding(src_tensor) * math.sqrt(model.d_model)))

    trg_indexes = [tgt_vocab['<bos>']]
    for i in range(max_length):
        trg_tensor = torch.LongTensor(trg_indexes).unsqueeze(0).to(device)
        # print("src_tensor:",src_tensor)
        # print("trg_tensor:",trg_tensor)
        with torch.no_grad():
            output = model(src_tensor, trg_tensor)
        
        pred_token = output.argmax(2)[:, -1].item()
        trg_indexes.append(pred_token)
        
        if pred_token == tgt_vocab['<eos>']:
            break
    
    trg_tokens = [tgt_vocab.get_itos()[i] for i in trg_indexes]
    return trg_tokens[1:-1]  # 移除<bos>和<eos>标记

def calculate_bleu(dev_loader, src_vocab, tgt_vocab, model, device):
    model.eval()
    translations = []
    references = []
    
    with torch.no_grad():
        for src, tgt in dev_loader:
            src = src.to(device)
            for sentence in src:
                translated = translate_sentence(sentence, src_vocab, tgt_vocab, model, device)
                translations.append(' '.join(translated))
            
            for reference in tgt:
                ref_tokens = [tgt_vocab.get_itos()[idx] for idx in reference if idx not in [tgt_vocab['<bos>'], tgt_vocab['<eos>'], tgt_vocab['<pad>']]]
                references.append([' '.join(ref_tokens)])
    
    bleu = sacrebleu.corpus_bleu(translations, references)
    return bleu.score

# 主训练循环
def train_model(model, train_iterator, valid_iterator, optimizer, criterion, N_EPOCHS = 10, CLIP = 1, save_path = '../model/best-model.pt'):
    best_valid_loss = float('inf')
    
    for epoch in range(N_EPOCHS):
        start_time = time.time()
        
        #print(f"Starting Epoch {epoch + 1}")
        train_loss = train(model, train_iterator, optimizer, criterion, CLIP)
        valid_loss = evaluate(model, valid_iterator, criterion)
        
        end_time = time.time()
        epoch_mins, epoch_secs = epoch_time(start_time, end_time)
        
        if valid_loss < best_valid_loss:
            best_valid_loss = valid_loss
            torch.save(model.state_dict(), save_path)
        
        print(f'Epoch: {epoch+1:02} | Time: {epoch_mins}m {epoch_secs}s')
        print(f'\tTrain Loss: {train_loss:.3f} | Train PPL: {math.exp(train_loss):7.3f}')
        print(f'\t Val. Loss: {valid_loss:.3f} |  Val. PPL: {math.exp(valid_loss):7.3f}')

N太大了，我把N改小了才运行的快点，N太大了会要很久的时间。

# 定义常量
MAX_LENGTH = 100  # 最大句子长度
BATCH_SIZE = 32
DEVICE = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
N = 148363   # 采样训练集的数量

train_path = '../dataset/train.txt'
dev_en_path = '../dataset/dev_en.txt'
dev_zh_path = '../dataset/dev_zh.txt'
test_en_path = '../dataset/test_en.txt'

train_loader, dev_loader, test_loader, en_vocab, zh_vocab = load_data(
    train_path, dev_en_path, dev_zh_path, test_en_path
)


print(f"英语词汇表大小: {len(en_vocab)}")
print(f"中文词汇表大小: {len(zh_vocab)}")
print(f"训练集大小: {len(train_loader.dataset)}")
print(f"开发集大小: {len(dev_loader.dataset)}")
print(f"测试集大小: {len(test_loader.dataset)}")

5、对测试集进行翻译

save_dir = '../results/submit_task2.txt'
with open(save_dir, 'w') as f:
    translated_sentences = []
    for batch in test_loader:  # 遍历所有数据
        src, _ = batch
        src = src.to(DEVICE)
        translated = translate_sentence(src[0], en_vocab, zh_vocab, model, DEVICE, max_length=50)  # 翻译结果,max_length生成翻译的最大长度
        #print(translated)
        results = "".join(translated)
        f.write(results + '\n')  # 将结果写入文件
    print(f"翻译完成，结果已保存到{save_dir}")

结果上传比赛平台得出分数。2024 iFLYTEK A.I.开发者大赛-讯飞开放平台