分词并构建词汇表
将文本映射为整数 id
分词并构建词汇表 是 CoddyKit 上的免费 Deep Learning Academy 课时。 这是第 1 节课，共 4 节。 你可以在下方免费阅读本课时的完整内容 — 然后在浏览器中使用内置代码编辑器和全天候 AI 导师进行实践。 这是 Deep Learning Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 Deep Learning Academy 课程共包含 4 节课。
本课时的部分内容尚未翻译，以英文显示。
Networks Only Eat Numbers
A neural net cannot read raw letters. Before any learning happens, you must turn text into numbers the model can crunch. 🔢
First Step: Tokenize
To tokenize means to split text into small pieces called tokens. The simplest choice is to split a sentence on spaces into words.
text = "I love deep learning"
tokens = text.split()
# ["I", "love", "deep", "learning"]Tokens Can Be Smaller
A token need not be a whole word. It can be a character or a sub-word piece, which helps the model handle rare or unseen words.
Build a Vocabulary
A vocabulary is the full set of unique tokens your model knows. You collect every distinct token across your training text.
Give Each Token an Id
Each unique token gets one integer id. This mapping from token to id is how words become numbers the network can index.
vocab = {"i": 0, "love": 1, "deep": 2, "learning": 3}Encode a Sentence
To encode text, you look up each token in the vocabulary and replace it with its id, producing a list of integers.
ids = [vocab[t] for t in ["i", "love", "deep"]]
# [0, 1, 2]Handle Unknown Words
Some tokens at test time were never seen in training. Map them to a special unknown token so the model still gets a valid id.
unk_id = vocab.get("dragons", vocab["<unk>"])Special Tokens Help
Add special tokens like padding, start, and end markers. They give the model structure beyond the plain words themselves.
Lowercase and Clean
Normalizing text by lowercasing and stripping punctuation shrinks the vocabulary so Cat and cat share a single id.
Limit the Vocabulary Size
Real corpora have huge vocabularies. Keep only the most frequent tokens to control the vocab size; the rest become unknown.
Now Text Is a Tensor
Once encoded, a sentence is a list of ids you can wrap in a tensor. The pipeline from raw text to model input is complete.
import torch
ids = torch.tensor([0, 1, 2, 3])Quick Check
What does building a vocabulary give every unique token?
Recap
You split text into tokens, gather the unique ones into a vocabulary, and map each to an integer id so text becomes numbers. ✅
常见问题解答
「分词并构建词汇表」课时是免费的吗？
是的 — 「分词并构建词汇表」的完整文本可在网页上免费阅读。要进行交互式练习（内置代码编辑器和全天候 AI 导师）并解锁 Deep Learning Academy 课程的其余内容，请升级到 CoddyKit PRO。 Deep Learning Academy 课程共包含 4 节课。
「分词并构建词汇表」这节课中我会学到什么？
将文本映射为整数 id 你通过在浏览器中直接运行的动手代码来练习 Deep Learning Academy，全天候 AI 导师会在你学习这节课的过程中回答你的问题。
学习 Deep Learning Academy 需要有经验吗？
无需任何先前经验。CoddyKit 上的 Deep Learning Academy 课程适合初学者到高级学习者，你可以从这里开始或从头开始，按照自己的节奏学习。 这是第 1 节课，共 4 节。
「分词并构建词汇表」课时需要多长时间？
大多数 CoddyKit 课程大约需要 5–10 分钟。每节课都很精短且互动，所以你能稳步进步，并在网页和应用中从离开的地方继续。
我能在这节 Deep Learning Academy 课中编写并运行代码吗？
能。每节 Deep Learning Academy 课都包含内置代码编辑器，你可以在浏览器中直接编写并运行真实代码，并获得即时 AI 反馈 — 无需本地设置。