♎
Limited AI
  • Machine Learning
    • Linear Model Cheating Sheet
    • Nonlinear Model Cheating Sheet
    • General Linear Model 1
    • General Linear Model 2
    • General Linear Model 3
    • Tree Based Methods
    • Tree Based Methods Supplement
    • XG,Cat,Light__Boosting
    • KNN&PCA
    • Model Performance
    • Model Evaluation
    • Code Practice
      • KNN
      • Decision Tree Python Code
    • Data and Feature Engineering
      • Handle Bias Data
      • Cold Start Problem
  • Deep Learning
    • Summary v2
    • Basic Neural Network
      • From Linear to Deep
      • Perceptron and Activation Function
      • NN network Details
      • Backpropagation Details
      • Gradient Vanishing vs Gradient Exploding
    • Basic CNN
      • Why CNN
      • Filter/ Convolution Kernel and Its Operation
      • Padding& Stride
      • Layers
      • Extra:From Fully Connected Layers to Convolutions
      • Extra: Multiple Input and Multiple Output Channels
    • Advance CNN
      • Convolutional Neural Networks(LeNet)
      • Deep Convolution Neural Networks(AlexNet)
      • Networks Using Blocks (VGG)
      • Network in Network(NiN)
      • Multi-Branch Networks(GoogLeNet&I mageNet)
      • Residual Networks(ResNet) and ResNeXt
      • Densely Connected Networks(DenseNet)
      • Batch Normalization
    • Basic RNN
      • Seq Model
      • Raw Text to Seq
      • Language Models
      • Recurrent Neural Networks(RNN)
      • Backpropagation Through Time
    • Advance RNN
      • Gated Recurrent Units(GRU)
      • Long Short-Term Memory(LSTM)
      • Bidirectional Recurrent Neural Networks(BRNN)
      • Encoder-Decoder Architecture
      • Seuqence to Sequence Learning(Seq2Seq)
    • Attention Mechanisms and Transformers
      • Queries, Keys, and Values
      • Attention is all you need
        • Attention and Kernel
        • Attention Scoring Functions
        • The Bahdanau Attention Mechanism
        • Multi-Head Attention
        • Self-Attention
        • Attention的实现
      • The Transformer Architecture
        • Extra Reading
        • 最短的最大路径长度
      • Large-Scaling Pretraning with Transformers
        • BERT vs OpenAI GPT vs ELMo
        • Decoder Model框架
        • Bert vs XLNet
        • T5& GPT& Bert比较
        • 编码器-解码器架构 vs GPT 模型
        • Encoder vs Decoder Reference
      • Transformers for Vision
      • Transformer for Multiomodal
    • NLP Pretraining
      • Word Embedding(word2vec)
        • Extra Reading
      • Approximate Training
      • Word Embedding with Global Vectors(GloVe)
        • Extra Reading
        • Supplement
      • Encoder(BERT)
        • BERT
        • Extra Reading
      • Decoder(GPT&XLNet&Lamma)
        • GPT
        • XLNet
          • XLNet架构
          • XLNet特点与其他比较
      • Encoder-Decoder(BART& T5)
        • BART
        • T5
  • GenAI
    • Introduction
      • GenAI Paper Must Read
      • GenAI六个阶段
    • Language Models Pre-training
      • Encoder-Decoder Architecture
      • Encoder Deep Dive
      • Decoder Deep Dive
      • Encoder VS Decoder
      • Attention Mechanism
      • Transformers
    • Example: Llama 3 8B架构
    • Fine-Tuning Generation Models
    • RAG and Adavance RAG
    • AI Agent
  • Statistics and Optimization
    • A/B testing
    • Sampling/ABtesting/GradientMethod
    • Gradient Decent Deep Dive
  • Machine Learning System Design
    • Extra Reading
    • Introduction
  • Responsible AI
    • AI Risk and Uncertainty
      • What is AI risk
      • General Intro for Uncertainty Quantification
      • Calibration
      • Conformal Prediction
        • Review the linear regression
        • Exchangeability
        • Split Conformal Prediction
        • Conformalized Quantile Regression
        • Beyond marginal coverage
        • Split Conformal Classification
        • Full Conformal Coverage
        • Cross-Validation +
        • Conformal Histgram Regression
    • xAI
      • SHAP value
  • Extra Research
    • Paper Reading
    • Reference
Powered by GitBook
On this page
  • Reading the Dataset
  • Tokenization
  • Vocabulary
  1. Deep Learning
  2. Basic RNN

Raw Text to Seq

Typical preprocessing pipelines execute the following steps:

  1. Load text as strings into memory. (text--> string)

  2. Split the strings into tokens (e.g., words or characters). (string --> token)

  3. Build a vocabulary dictionary to associate each vocabulary element with a numerical index. (vocabulary dict)

  4. Convert the text into sequences of numerical indices. (dict --> numerical indices)

Reading the Dataset

  • just read..... or might you need to ignore punctuation and capitalization when preprocessing the raw text

Tokenization

  • Tokens are the atomic (indivisible) units of text. Each time step corresponds to 1 token, but what precisely constitutes a token is a design choice.(token是最小的元素)

  • Sometimes, we tokenize our preprocessed text into a sequence of characters.

Vocabulary

  • vocabularies, i.e., objects that associate each distinct token value with a unique index

  • 我们先将训练集中的所有文档合并在一起，对它们的唯一词元进行统计， 得到的统计结果称之为语料（corpus）。 然后根据每个唯一词元的出现频率，为其分配一个数字索引。

  • 很少出现的词元通常被移除，这可以降低复杂性。 另外，语料库中不存在或已删除的任何词元都将映射到一个特定的未知词元“<unk>”。 我们可以选择增加一个列表，用于保存那些被保留的词元， 例如：填充词元（“<pad>”）； 序列开始词元（“<bos>”）； 序列结束词元（“<eos>”）。

Wrap Up

  • 在使用上述函数时，我们将所有功能打包到load_corpus_time_machine函数中， 该函数返回corpus（词元索引列表）和vocab（时光机器语料库的词表）。 我们在这里所做的改变是：

    1. 为了简化后面章节中的训练，我们使用字符（而不是单词）实现文本词元化；

    2. 时光机器数据集中的每个文本行不一定是一个句子或一个段落，还可能是一个单词，因此返回的corpus仅处理为单个列表，而不是使用多词元列表构成的一个列表。

PreviousSeq ModelNextLanguage Models

Last updated 8 months ago