0Pricing
NLP Academy · 课时

词形还原：更智能的基本形式

将词语还原为真实的词典形式

词形还原：更智能的基本形式 是 CoddyKit 上的免费 NLP Academy 课时。 这是第 4 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 NLP Academy 学习路径的一部分，你的进度在网页和 CoddyKit 应用中同步。 NLP 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。

A Smarter Reducer

Stemming chops blindly, but lemmatization reduces a word to its real dictionary base form, called the lemma. The result is always a proper word. 📖

Lemma vs Stem

Stemming turns studies into studi, but lemmatization returns the clean lemma study. That tidy, valid output is the big win of lemmatization.

It Uses a Vocabulary

A lemmatizer looks words up in a real vocabulary like WordNet. That lookup is what lets it know better is the base form better, not bett.

The WordNet Lemmatizer

NLTK provides the WordNetLemmatizer. Create one, then call lemmatize on a word to get its base form back.

from nltk.stem import WordNetLemmatizer
lem = WordNetLemmatizer()
print(lem.lemmatize('cars'))

Part of Speech Matters

By default the lemmatizer assumes every word is a noun. So the verb running stays running unless you tell it the word is a verb.

print(lem.lemmatize('running'))

Pass the Right Tag

Give it the pos argument to fix that. Telling the lemmatizer the word is a verb reduces running all the way down to its base form run.

print(lem.lemmatize('running', pos='v'))

Irregular Forms Handled

Because it knows real grammar, the lemmatizer maps tricky words too. The verb went correctly becomes its base form go, something a stemmer cannot do.

print(lem.lemmatize('went', pos='v'))

Adjectives and Plurals

It handles other word types as well. With the adjective tag, the lemmatizer turns better into its base form good.

print(lem.lemmatize('better', pos='a'))

Lemmatize a Token List

Apply it across a document with a comprehension, just like stemming. Each token comes back as a clean, valid base form.

words = ['dogs', 'boxes', 'wishes']
print([lem.lemmatize(w) for w in words])

Slower but Sharper

Lemmatization needs a dictionary and ideally part-of-speech tags, so it runs slower than stemming. You trade speed for cleaner, more accurate results. ⚖️

Which Should You Pick?

Use stemming for fast, large-scale search and lemmatization when readable, accurate base forms matter, like building features for a model.

Quick Check

Let's compare the two reducers.

Recap

You learned lemmatization uses a vocabulary and part-of-speech tags to return real base forms. It is slower than stemming but far cleaner. Great job! 🎉

常见问题解答

「词形还原：更智能的基本形式」课时是免费的吗？

是的 — 「词形还原：更智能的基本形式」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 NLP Academy 课程的其余内容，请升级到 CoddyKit PRO。 NLP Academy 课程共包含 4 节课。

「词形还原：更智能的基本形式」这节课中我会学到什么？

将词语还原为真实的词典形式 你通过在浏览器中直接运行的动手代码来练习 NLP 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 NLP Academy 需要有经验吗？

无需任何先前经验。CoddyKit 上的 NLP 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 4 节课，共 4 节。

「词形还原：更智能的基本形式」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 NLP Academy 课中编写并运行代码吗？

能。每节 NLP 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。

此课程中的所有课时

  1. 大小写与空格为何重要
  2. 转换为小写并去除空白
  3. 词干提取：截取词根
  4. 词形还原：更智能的基本形式
← 返回 NLP Academy